No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Effects of Sentiment-Based Sonification on Fairy Tale Listening Experience
ResearchGate has not been able to resolve any citations for this publication.
Making the link between human emotion and music is challenging. Our aim was to produce an efficient system that emotionally rates songs from multiple genres. To achieve this, we employed a series of online self-report studies, utilising Russell's circumplex model. The first study (n = 44) identified audio features that map to arousal and valence for 20 songs. From this, we constructed a set of linear regressors. The second study (n = 158) measured the efficacy of our system, utilising 40 new songs to create a ground truth. Results show our approach may be effective at emotionally rating music, particularly in the prediction of valence.
Social networking platforms have become an essential means for communicating feelings to the entire world due to rapid expansion in the Internet era. Several people use textual content, pictures, audio, and video to express their feelings or viewpoints. Text communication via Web-based networking media, on the other hand, is somewhat overwhelming. Every second, a massive amount of unstructured data is generated on the Internet due to social media platforms. The data must be processed as rapidly as generated to comprehend human psychology, and it can be accomplished using sentiment analysis, which recognizes polarity in texts. It assesses whether the author has a negative, positive, or neutral attitude toward an item, administration, individual, or location. In some applications, sentiment analysis is insufficient and hence requires emotion detection, which determines an individual’s emotional/mental state precisely. This review paper provides understanding into levels of sentiment analysis, various emotion models, and the process of sentiment analysis and emotion detection from text. Finally, this paper discusses the challenges faced during sentiment and emotion analysis.
As an agent delivers content during the communication between an artificial intelligence (AI) machine and a person, the voice of the agent is a crucial factor to be considered. Particularly in the fields of eHealth, the perception of users toward an agent is crucial as it significantly affects the communication between the agent and its patients, as well as the treatment results. Thus, this study examined the effects of the voice of an agent on the perception of users toward the agent and its counseling effects. This study developed a psychological counseling agent with four voices according to gender and age, communicated with the subjects through such agent, and measured the perception of users toward the agent and its counseling effects through a questionnaire. Results demonstrated that the female-voiced agent had a higher level of attractiveness than the male-voiced agent, regardless of the age of such voice, and the agent using an older voice had a higher level of expertness and depth than the agent using a younger voice, regardless of the gender of such voice. The findings of this study are expected to be effectively used to design a voice-based AI agent that considers the optimal voice according to the purpose of use.
We connected theory and research on narrative persuasion to the literature on social robots and examined the effects of a robotic storyteller’s facial expressions. The congruency between the emotional arc of a story and the facial expressions of the robot was of particular interest. In a lab experiment, participants were confronted with a storytelling robot who displayed emotions that were congruent or incongruent with the events unfolding in the story or it displayed no emotions. Affect congruency increased participants’ transportation in the story world, led to more positive evaluations of the robot, and increased the likelihood of choosing a product that was advertised in the story. Although the robot’s voice was held constant in all three conditions, congruent facial expressions led to the illusion of a more congruent intonation by the robot.
Music is one of the effective media to convey emotion. Emotion recognition in music is the process of identifying the emotion from the music clips. In this paper, a novel approach is proposed to recognize the emotion by classes of musical instruments using deep learning techniques. Music dataset is collected for four instrument types, string, percussion, woodwind, and brass. These instruments types are grouped into four emotions, happy, sad, neutral and fear. The Mel frequency cepstral coefficients (MFCC), Chroma energy normalized statistics (CENS), chroma short time Fourier transform (STFT), spectral features spectral centroid, bandwidth, rolloff, and temporal feature ZCR are extracted from the instrumental music data set. Based on the extracted features recurrent neural networks (RNN) are trained to recognize the emotion. The performance of RNN is compared with the baseline machine learning classification algorithms. The results indicate that MFCC features with deep RNN give better performance for instrument emotion recognition. It also shows that instrument class plays an important role in the emotion induced by the music. Music is one of the effective media to convey emotion. Emotion recognition in music is the process of identifying the emotion from the music clips. In this paper, a novel approach is proposed to recognize the emotion by classes of musical instruments using deep learning techniques. Music dataset is collected for four instrument types, string, percussion, woodwind, and brass. These instruments types are grouped into four emotions, happy, sad, neutral and fear. The Mel frequency cepstral coefficients (MFCC), Chroma energy normalized statistics (CENS), Chroma short time Fourier transform (STFT), spectral features spectral centroid, bandwidth, rolloff, and temporal feature ZCR are extracted from the instrumental music data set. Based on the extracted features recurrent neural networks (RNN) are trained to recognize the emotion. The performance of RNN is compared with the baseline machine learning classification algorithms. The results indicate that MFCC features with deep RNN give better performance for instrument emotion recognition. It also shows that instrument class plays an important role in the emotion induced by the music.
Recent research has shown that different musical instrument sounds have strong emotional characteristics. It has also shown how these emotional characteristics change with different pitch and dynamics for the piano and solo bowed strings. This paper investigates how the emotional characteristics of the section bowed strings vary with pitch and dynamics, comparing and contrasting the solo and section string results. We conducted listening tests where listeners compared the section string sounds pairwise over ten emotional categories. The section and solo string results were somewhat similar overall, but with some notable differences as well. The emotional characteristics Happy, Heroic, Romantic, Comic, Calm, and Shy generally increased with pitch in an arching shape that peaked at C5 and decreased at the highest pitches. The characteristics Angry and Sad generally decreased with pitch. Scary was somewhat U-shaped and especially strong in the extreme high register. In terms of dynamics, the results showed that Happy, Heroic, Comic, Angry, and Scary were stronger for loud notes, while Romantic, Calm, Shy, and Sad were stronger for soft notes. These results provide audio engineers and musicians with possible suggestions for emphasizing various emotional characteristics of the section strings in orchestral recordings and performances.
This study examined the impact of noise on cognitive performance in autism spectrum disorder (ASD), while concurrently measuring sympathetic responses. Adolescents with and without ASD completed visually presented span tasks in a 2 × 2 experimental manipulation of noise (quiet vs. 75 dB gated broadband noise) and task difficulty (easier vs. harder). Analyses revealed a significant noise × difficulty interaction on performance, and a significant group × noise × difficulty interaction on sympathetic arousal. Correlational analyses indicated an adaptive effect of noise and increased arousal on performance in the easier condition for the control group and a detrimental effect of noise and increased arousal in the harder condition for the ASD group. Implications for sensory processing research and intervention development are discussed.
As qualitative research becomes increasingly recognized and valued, it is imperative that it is conducted in a rigorous and methodical manner to yield meaningful and useful results. To be accepted as trustworthy, qualitative researchers must demonstrate that data analysis has been conducted in a precise, consistent, and exhaustive manner through recording, systematizing , and disclosing the methods of analysis with enough detail to enable the reader to determine whether the process is credible. Although there are numerous examples of how to conduct qualitative research, few sophisticated tools are available to researchers for conducting a rigorous and relevant thematic analysis. The purpose of this article is to guide researchers using thematic analysis as a research method. We offer personal insights and practical examples, while exploring issues of rigor and trustworthiness. The process of conducting a thematic analysis is illustrated through the presentation of an auditable decision trail, guiding interpreting and representing textual data. We detail our step-by-step approach to exploring the effectiveness of strategic clinical networks in Alberta, Canada, in our mixed methods case study. This article contributes a purposeful approach to thematic analysis in order to systematize and increase the traceability and verification of the analysis.
This paper investigates the important role of narrative in social science case-based research. The focus is on the use of narrative in creating a productive ordering of the materials within such cases, and on how such ordering functions in relation to ‘narrative explanation’. It argues that narrative ordering based on juxtaposition - using an analogy to certain genres of visual representation - is associated with creating and resolving puzzles in the research field. Analysis of several examples shows how the use of conceptual or theoretical resources within the narrative ordering of ingredients enables the narrative explanation of the case to be resituated at other sites, demonstrating how such explanations can attain scope without implying full generality.
Advances in computing power, natural language processing, and digitization of text now make it possible to study our a culture's evolution through its texts using a "big data" lens. Our ability to communicate relies in part upon a shared emotional experience, with stories often following distinct emotional trajectories, forming patterns that are meaningful to us. Here, by classifying the emotional arcs for a filtered subset of 1,737 stories from Project Gutenberg's fiction collection, we find a set of six core trajectories which form the building blocks of complex narratives. We strengthen our findings by separately applying optimization, linear decomposition, supervised learning, and unsupervised learning. For each of these six core emotional arcs, we examine the closest characteristic stories in publication today and find that particular emotional arcs enjoy greater success, as measured by downloads.
The acoustical qualities within a classroom are referred to as its soundscape. Classrooms are environments full of sounds and student learning depends largely on how well the relevant messages are discerned within its soundscape. In the ideal classroom, the message is heard and understood with little or no effort. When teachers must raise their voices in order to be heard the listener may not get a clear signal across the full range of speech sounds. Being able to focus on relevant sounds is a fundamental factor accounting for learning the phonology of speech which underlies learning to read and write. Reverberation, noise, and distance between the speaker and listeners all contribute to the classroom soundscape. Student characteristics also contribute including hearing impairment, developmental disabilities, and specific deficits in learning, attention, speech, language, or auditory processing. In addition, second language learners cannot rely on previous linguistic experience and must depend more heavily on hearing the spoken messages accurately. The use of sound-field amplification has received a great deal of attention in the literature. Benefits of this technology include improved attention and learning in students as well as improved vocal health in teachers. The classroom environment has been described as more calm and relaxed when the soundscape is favourable. This paper reviews the literature and draws conclusions about these acoustical features which are essential for an optimal learning environment.
Telling engaging stories is an interesting ability for an artificial companion for children. Three features can be made engaging: the agent itself (which is addressed by the field of Embodied Conversational Agents); the content of the story (e.g. interactive stories [1]); and the way the story is narrated. We designed and implemented engaging narrative strategies for Reeti, an affective expressive robot with a wide range of emotional facial expressions.
Two experiments were conducted to investigate the final-tone extrapolating behavior of two music experts, one of Western classical music and the other of Japanese traditional music. The first experiment verified sehema-driven properties of the experts’ melody cognition. Both experts’ final tone extrapolation was highly rule-govemed, but the underlying properties of their melodic schema seemed quite different. The Western classical music expert tended to process given melodies within the Western diatonic tonal frame, while the Japanese traditional music expert tended to operate "bimusically." That is, the latter processed some stimulus tone sequences based on the Japanese traditional tonal frame, but processed others based on the diatonic tonal frame. It was also confirmed that the melodic cognition of the Western music expert was more harmony-oriented, while that of the Japanese music expert was relatively contour-oriented. The second experiment conducted a more detailed investigation of the Western music experts’ rules in extrapolating the final tones. Only the relationship between the responses of this expert and the Western diatonic scale structures was focused on. The response structures of this expert were analyzed in contrast to her subjective tonal structures for stimulus melodies and are discussed in terms of her tonal schema.
This paper describes the implementation in a walking humanoid robot of a mental model, allowing the dynamical change of the emotional state of the robot based on external stimuli; the emotional state affects the robot decisions and behavior, and it is expressed with both facial and whole-body patterns. The mental model is applied to KOBIAN-R, a 65-DoFs whole body humanoid robot designed for human-robot interaction and emotion expression. To evaluate the importance of the proposed system in the framework of human-robot interaction and communication, we conducted a survey by showing videos of the robot behaviors to a group of 30 subjects. The results show that the integration of dynamical emotion expression and locomotion makes the humanoid robot more appealing to humans, as it is perceived as more “favorable” and “useful”, and less “robot-like".
Factor-analytic evidence has led most psychologists to describe affect as a set of dimensions, such as displeasure, distress, depression, excitement, and so on, with each dimension varying independently of the others. However, there is other evidence that rather than being independent, these affective dimensions are interrelated in a highly systematic fashion. The evidence suggests that these interrelationships can be represented by a spatial model in which affective concepts fall in a circle in the following order: pleasure (0), excitement (45), arousal (90), distress (135), displeasure (180), depression (225), sleepiness (270), and relaxation (315). This model was offered both as a way psychologists can represent the structure of affective experience, as assessed through self-report, and as a representation of the cognitive structure that laymen utilize in conceptualizing affect. Supportive evidence was obtained by scaling 28 emotion-denoting adjectives in 4 different ways: R. T. Ross's (1938) technique for a circular ordering of variables, a multidimensional scaling procedure based on perceived similarity among the terms, a unidimensional scaling on hypothesized pleasure–displeasure and degree-of-arousal dimensions, and a principal-components analysis of 343 Ss' self-reports of their current affective states. (70 ref) (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Thematic analysis is a poorly demarcated, rarely acknowledged, yet widely used qualitative analytic method within psychology. In this paper, we argue that it offers an accessible and theoretically flexible approach to analysing qualitative data. We outline what thematic analysis is, locating it in relation to other qualitative analytic methods that search for themes or patterns, and in relation to different epistemological and ontological positions. We then provide clear guidelines to those wanting to start thematic analysis, or conduct it in a more deliberate and rigorous way, and consider potential pitfalls in conducting thematic analysis. Finally, we outline the disadvantages and advantages of thematic analysis. We conclude by advocating thematic analysis as a useful and flexible method for qualitative research in and beyond psychology.
Engaging storytelling is a necessary skill for humanoid robots if they are to be used in education and entertainment applications. Storytelling requires that the humanoid robot be aware of its audience and able to direct its gaze in a natural way. In this paper, we explore how human gaze can be modeled and implemented on a humanoid robot to create a natural, human-like behavior for storytelling. Our gaze model integrates data collected from a human storyteller and a discourse structure model developed by Cassell and her colleagues for human-like conversational agents (1994). We used this model to direct the gaze of a humanoid robot, Honda's ASIMO, as he recited a Japanese fairy tale using a pre-recorded human voice. We assessed the efficacy of this gaze algorithm by manipulating the frequency of ASIMO's gaze between two participants and used pre and post questionnaires to assess whether participants evaluated the robot more positively and did better on a recall task when ASIMO looked at them more. We found that participants performed significantly better in recalling ASIMO's story when the robot looked at them more. Our results also showed significant differences in how men and women evaluated ASIMO based on the frequency of gaze they received from the robot. Our study adds to the growing evidence that there are many commonalities between human-human communication and human-robot communication
The idea behind sonification is that synthetic nonverbal sounds can represent numerical data and provide support for information processing activities of many differentkinds. This article describes some of the ways that sonification has been used in assistive technologies, remote collaboration, engineering analyses, scientific visualisations, emergency services and aircraft cockpits. Approaches for designing sonifications are surveyed, and issues raised by the existing approaches and applications are outlined. Relationsare drawn to other areas of knowledge where similar issueshave also arisen, such as human-computer interaction, scientific visualisation, and computer music. At the end is a listof resources that will help you delve further into the topic.
We discuss issues in designing virtual humans for applications which require long-term voluntary use, and the problem of maintaining engagement with users over time. Concepts and theories related to engagement from a variety of disciplines are reviewed. We describe a platform for conducting studies into long-term interactions between humans and virtual agents, and present the results of two longitudinal randomized controlled experiments in which the effect of manipulations of agent behavior on user engagement was assessed.
The pandemic is not one coherent narrative but an unbounded multiplicity of narrative ravellings. One theme that can be traced through the course of the past two years is the undoings and redoings of normalcy, including normalcy in qualitative research. Our digital literacy research group took up the pandemic as a canvas upon which to story new futurities and possibilities for qualitative research in physical separation within the context of slow-moving upheaval. At the outset of the first physical lockdown in March of 2020, we began a collaborative and multimodal futures fictioning practice, storying new communicative possibilities and potentialities. Over the course of fourteen months, we reached into each other’s imagination, isolation, temporality, and physical environment via story and sound. This exposition charts our diffractive fictioning methodology, in which we collectively map communicative practices and collaborative meaning in virtual spaces in a time when coherence and consensus have become radically fractured. A cyborg skunk moves through this assemblage of poetry, sonification, narrative, performance, theory, and silence, flicking its many imagined tales and nudging its noses at the wreckage of the normal in search of difference.
As robots have become more pervasive in our everyday life, social aspects of robots have attracted researchers’ attention. Because emotions play a crucial role in social interactions, research has been conducted on conveying emotions via speech. Our study sought to investigate the synchronization of multimodal interaction in human-robot interaction (HRI). We conducted a within-subjects exploratory study with 40 participants to investigate the effects of non-speech sounds (natural voice, synthesized voice, musical sound, and no sound) and basic emotions (anger, fear, happiness, sadness, and surprise) on user perception with emotional body gestures of an anthropomorphic robot (Pepper). While listening to a fairytale with the participant, a humanoid robot responded to the story with a recorded emotional non-speech sounds and gestures. Participants showed significantly higher emotion recognition accuracy from the natural voice than from other sounds. The confusion matrix showed that happiness and sadness had the highest emotion recognition accuracy, which is in line with previous research. The natural voice also induced higher trust, naturalness, and preference, compared to other sounds. Interestingly, the musical sound mostly showed lower perception ratings, even compared to the no sound. Results are discussed with design guidelines for emotional cues from social robots and future research directions.
With the advancements of machine learning and AI technologies, robots have been more widely used in our everyday life and they have also been used in education. The present study introduces a 12-week child-robot theater afterschool program designed to promote science, technology, engineering, and mathematics (STEM) education with art elements (STEAM) for elementary students using social robots. Four modules were designed to introduce robot mechanisms as well as arts: Acting (anthropomorphism), Dance (robot movements), Music and Sounds (music composition), and Drawing (robot art). These modules provided children with basic knowledge about robotics and STEM and guided children to create a live robot theater play. A total of 16 students participated in the program, and 11 of them were involved in completing questionnaires and interviews regarding their perceptions towards robots, STEAM, and the afterschool program. Four afterschool program teachers participated in interviews, reflecting their perceptions of the program and observations of children’s experiences during the program. Our findings suggest that the present program effectively maintained children’s engagement and improved their interest in STEAM by connecting social robots and theater production. We conclude with design guidelines and recommendations for future research and programs.
Research has suggested that background music can have a positive or negative effect that can influence the affective state of individuals. Although research has demonstrated that fear negatively influences our cognitive performance, there is a research gap in understanding the combined effects of different background music tempo and fear in influencing reading comprehension performance. Data were collected from 70 participants enrolled at a public university in Canada. Participants were required to listen to background music of varying speeds with three conditions (no music, slow music and fast music). We adopted a cross‐sectional multi‐level modelling approach for the main analyses, and further analyses using t‐test and ANOVA. Results indicated that expression of fear was not a significant predictor of participants' reading comprehension performance (Model 1). However, when music condition was added (Model 2) in addition to expression of fear, a significant relationship between reading comprehension performance and music condition was found, showing better reading comprehension performance in the slow music condition than in the no music condition. Furthermore, there was a significant interaction effect between music condition and expression of fear on reading comprehension performance (Model 3). Importantly, not all individuals were affected by the music to the same extent, with the possibility that baseline level of fear being the key issue in influencing comprehension performance. Considering both expression of fear and music condition is required to understand the combined effects on cognitive performance. Expression of fear during cognitive tasks such as reading could be an essential signal that interventions should be applied. Such strategies may be especially beneficial for task performers with higher baseline levels of fear and possibly provide us with insights for best practice and research implications in the field of reading comprehension among individuals with special needs. What is already known about this topic Background music can influence our emotions, including fear, which in turn affect learning, whereas certain affective states such as fear can potentially negatively affect learning. Music tempo can influence reading comprehension performance, which could be the result of cognitive load. There is no consensus about the combined effect of background music and fear on our mind during cognitively demanding tasks such as reading comprehension. What this paper adds Expression of fear itself was not a significant predictor of reading comprehension performance in different background music conditions. There was a significant interaction effect between music condition and expression of fear on reading comprehension performance, with the negative relationship between fear and reading comprehension performance was reduced in the no music condition or amplified in the fast music condition. Not all participants were affected to the same extent by the background music, with the individual's baseline level of fear hypothesized to be the key issue. Implications for theory, policy or practice We need to consider both the individual's affective state (expression of fear) and the environment (different background music conditions) for understanding the impacts on cognitive performance (e.g., reading comprehension performance). Although expression of fear itself cannot predict cognitive performance, expression of fear is still crucial for understanding the potential impacts by background music, because it affects the degree of impacts on cognitive performance. Interventions such as offering noise‐cancelling headphones and teaching relaxation strategies may be especially beneficial for certain task performers (e.g., some typically developing individuals and people with special needs such as autism) who perceive music/noise as distracting or for those with higher or unstable baseline levels of fear who need to work in a non‐quiet environment.
As the influence of social robots in people’s daily lives grows, research on understanding people’s perception of robots including sociability, trust, acceptance, and preference becomes more pervasive. Research has considered visual, vocal, or tactile cues to express robots’ emotions, whereas little research has provided a holistic view in examining the interactions among different factors influencing emotion perception. We investigated multiple facets of user perception on robots during a conversational task by varying the robots’ voice types, appearances, and emotions. In our experiment, 20 participants interacted with two robots having four different voice types. While participants were reading fairy tales to the robot, the robot gave vocal feedback with seven emotions and the participants evaluated the robot’s profiles through post surveys. The results indicate that (1) the accuracy of emotion perception differed depending on presented emotions, (2) a regular human voice showed higher user preferences and naturalness, (3) but a characterized voice was more appropriate for expressing emotions with significantly higher accuracy in emotion perception, and (4) participants showed significantly higher emotion recognition accuracy with the animal robot than the humanoid robot. A follow-up study ([Formula: see text]) with voice-only conditions confirmed that the importance of embodiment. The results from this study could provide the guidelines needed to design social robots that consider emotional aspects in conversations between robots and users.
In the present study a sonification of running data was evaluated. The aim of the sonification was to both convey information about the data and convey a specific emotion. The sonification was evaluated in three parts, firstly as an auditory graph, secondly together with additional text information, and thirdly together with an animated visualization, with a total of 150 responses. The results suggest that the sonification could convey an emotion similar to that intended, but at the cost of less good representation of the data. The addition of visual information supported understanding of the sonification, and the auditory representation of data. The results thus suggest that it is possible to design sonification that is perceived as both interesting and fun, and convey an emotional impression, but that there may be a trade off between musical experience and clarity in sonification.
We evaluate the effects of multisensory training on letters, including sonification of graphic symbols. We used “spatial sonification” where letter handwriting movements recorded in a two dimensional plan, vertical and horizontal, are systematically assigned to two acoustic features, spectral composition for the horizontal axis and frequency for the vertical axis. Forty-six kindergarten children were recruited. They were randomly assigned to three multisensory training groups: with sonification (Son) of letters, with a melody unrelated to the shape of the letters (Mel) and without any sound (Sil). We observed a significant effect of training, with the Son group performing better than the other groups in the reading and spelling tasks. We also observed a modification of two kinematic cues (time and in-air time) during handwriting, also in the Son group. We conclude that letter sonification could act as a binder between the visual and auditory dimensions of the letter. The processes underlying this benefit are discussed in the light of the Act-In model, a cognition memory model.
In human-robot interaction, natural and intuitive communication between robot and human is one of the most important research topics. Emotion plays a crucial role to make natural and social interactions. Research has focused more on robots’ appearances and facial emotional expressions, but little research has investigated robots’ voices and their mixed effects with robot types and different emotions for users to perceive robots’ emotional states. In this study, anthropomorphic and zoomorphic robots, four different voice types, and seven different emotional voices were used as mixed factors to discuss how these influence users’ perception on robots’ emotional expression and other characteristics. Sixteen participants were asked to read fairy tales to robots and determine robots’ emotional states when the robots verbally responded. Overall, the anthropomorphic robot (Nao) was preferred over the zoomorphic robot (Pleo), but this appearance did not influence emotion recognition accuracy or other robot characteristics. Participants showed lower accuracy in recognizing negative emotions with high arousal: anger, fear, and disgust. TTS was rated lower than other human voices in all robot characteristics, such as warmth, honesty, trustworthiness, and naturalness. Implications and design directions are discussed with the results.
Gain the technical and business insight needed to plan, deploy, and manage the services provided by the Microsoft Azure cloud. This second edition focuses on improving operational decision tipping points for the professionals leading DevOps and security teams. This will allow you to make an informed decision concerning the workloads appropriate for your growing business in the Azure public cloud.
Microsoft Azure starts with an introduction to Azure along with an overview of its architecture services such as IaaS and PaaS. You’ll also take a look into Azure’s data, artificial intelligence, and machine learning services. Moving on, you will cover the planning for and adoption of Azure where you will go through budgeting, cloud economics, and designing a hybrid data center. Along the way, you will work with web apps, network PaaS, virtual machines, and much more.
The final section of the book starts with Azure data services and big data with an in-depth discussion of Azure SQL Database, CosmosDB, Azure Data Lakes, and MySQL. You will further see how to migrate on-premises databases to Azure and use data engineering. Next, you will discover the various Azure services for application developers, including Azure DevOps and ASP.NET web apps. Finally, you will go through the machine learning and AI tools in Azure, including Azure Cognitive Services.
You will:
• Apply design guidance and best practices using Microsoft Azure to achieve business growth
• Create and manage virtual machines
• Work with AI frameworks to process and analyze data to support business decisions and increase revenue Deploy, publish, and monitor a web app
With a view to studying the development of social relationships between humans and robots, it is our contention that music can help provide extended engagement and open ended interaction. In this paper we explore the effectiveness of music as a mode of engagement using Mortimer, a robot able to play a drum kit and employing a composition algorithm to respond to a human pianist. We used this system to conduct a comparative study into the effects of presenting the robot as a social actor or as an instrument. Using automated behavioural metrics, including face tracking, we found that participants in the social actor condition played for longer uninterrupted and stopped the robot mid-performance less. They also spent more time looking at the robot when not playing and less time looking at the piano when playing. We suggest these results indicate greater fluency of playing and engagement and more feelings of social presence towards the robot when presented as a social actor
The ability to accurately represent sentences is central to language
understanding. We describe a convolutional architecture dubbed the Dynamic
Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of
sentences. The network uses Dynamic k-Max Pooling, a global pooling operation
over linear sequences. The network handles input sentences of varying length
and induces a feature graph over the sentence that is capable of explicitly
capturing short and long-range relations. The network does not rely on a parse
tree and is easily applicable to any language. We test the DCNN in four
experiments: small scale binary and multi-class sentiment prediction, six-way
question classification and Twitter sentiment prediction by distant
supervision. The network achieves excellent performance in the first three
tasks and a greater than 25% error reduction in the last task with respect to
the strongest baseline.
The present investigation, conducted on music students and non-music students as well as middle-aged subjects, had two aims. The first was to try to discover, through a synaesthetic bias, whether there is a difference in emotional reactions to the many musical modes in existence in Japan. The second was to make a comparison between age groups of the way in which melodies which differ only in one aspect, namely musical mode, are heard. The results show that (1) each mode produced a different impression, according to melodic type, on the listeners, but (2) there were additional differences in the emotional modal characters according to age group and to whether the listeners were musicians or non-musicians.
This paper presents a music mood classification model based on arousal-valence (AV) values for music recommendation system. We analyse the collected music mood tags and AV values from 10 subjects and classify music mood on the AV plane into 8 regions by using k-means clustering algorithm. For each region, we propose representative mood tags by using statistics. We find that some regions can be identified by representative mood tags like previous models but some mood tags are overlapped in almost regions. The proposed model can express a region with several representative moods and a mood distributed uniformly in almost regions.
Narrative media music, music used for narrative purposes in multimedia such as film, television or computer games, is becoming one of the largest sources of musical experience in our daily lives. Though typically experienced on an unconscious and unreflected level, this kind of music actively contributes narrative meaning in multimodal interplay with image, speech and sound effects. Often, what we (think we) see is to a large degree determined by what we hear. Using Halliday's (1978) metafunctions of communication as a starting point, two short film scenes (from Jaws and The Secret of My Success) are examined, with a focus on the intermodal relationships of music and image. The examples illustrate how musical and visual expressions combine to form multimodal statements where the whole is certainly different than the sum of the parts.
Narrative Intelligence (NI) — the confluence of narrative, Artificial Intelligence, and media studies — studies, models, and supports the human use of narrative to understand the world. This volume brings together established work and founding documents in Narrative Intelligence to form a common reference point for NI researchers, providing perspectives from computational linguistics, agent research, psychology, ethology, art, and media theory. It describes artificial agents with narratively structured behavior, agents that take part in stories and tours, systems that automatically generate stories, dramas, and documentaries, and systems that support people telling their own stories. It looks at how people use stories, the features of narrative that play a role in how people understand the world, and how human narrative ability may have evolved. It addresses meta-issues in NI: the history of the field, the stories AI researchers tell about their research, and the effects those stories have on the things they discover. (Series B)
This paper explores one way to use music in the context of affec-tive design. We've made a real-time music generator that is de-signed around the concepts of valence and arousal, which are two components of certain models of emotion. When set to a desired valence and arousal, the algorithm plays music corresponding to the intersection of these two parameters. We designed our algo-rithm using psychological theory of emotion and parametrized features of music which have been tested for affect. The results are a modular algorithm design, in which our parameters can be implemented in other affective music algorithms. We describe our implementation of these parameters, and our strategy for ma-nipulating the parameters to generate musical emotion. Finally we discuss possible applications for these techniques in the fields of the arts, medical systems, and research applications. We be-lieve that further work will result in a music generator which can produce music in any of a wide variety of commonly-perceived emotional connotations on command.
Although much research has explored emotional responses to music using single musical elements, none has explored the interactive effects of mode, texture, and tempo in a single experiment. To this end, a 2 (mode: major vs. minor) 2 (texture: nonharmonized vs. harmonized) 3 (tempo: 72, 108, 144 beats per min) within-participants experimental design was employed, in which 177 college students rated four, brief musical phrases on continuous happy-sad scales. Major keys, nonharmonized melodies, and faster tempos were associated with happier responses, whereas their respective opposites were associated with sadder responses. These effects were also interactive, such that the typically positive association between tempo and happiness was inverted among minor, nonharmonized phrases. Some of these effects were moderated by the gender and amount of musical experience of participants. A principal components analysis of responses to the stimuli revealed one negatively and one positively valenced factor of emotional musical stimuli.
One voice, different tunes: issues raised by dual analysis of a segment of qualitative data
Qualitative data analysis is a complex and contested part of the research process that has received limited theoretical attention. This paper explores the relationship between the way in which data are analysed and the nature of findings that emerge. It does this in response to demands to recognize the multiple voices that inform representations of reality, and debates about whether the interpretation of data reveals or constructs meaning. A small segment of data provided by one informant is subjected to both thematic and narrative analysis and the different perspectives that emerge are discussed with reference to whether different kinds of analysis lead to different kinds of meaning being imputed to the same text. The paper suggests that, rather than provide a unified and ever-more refined version of ‘reality’, the use of dual or multiple analysis helps to elucidate alternative interpretations of the data which might escape consideration with the use of a single approach.
- Del Negro Janice M
Microsoft’s new neural text-to-speech service Accessed 4
- Microsoft