About
172
Publications
60,052
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,349
Citations
Introduction
Dorien Herremans is an Associate Professor at Singapore University of Technology and Design, where she leads the Audio, Music, and AI (AMAAI) Lab. Her research focuses on developing cutting-edge AI technologies for multimodal applications, with a focus on generative models and affective computing.
Current institution
Additional affiliations
March 2006 - August 2008
August 2017 - July 2020
August 2017 - present
Publications
Publications (172)
Record companies invest billions of dollars in new talent around the globe each year. Gaining insight into what actually makes a hit song would provide tremendous benefits for the music industry. In this research we tackle this question by focussing on the dance hit song classification problem. A database of dance hit songs from 1985 until 2013 is...
Automatic music generation systems have gained in popularity and sophistication as advances in cloud computing have enabled large-scale complex computations such as deep models and optimization algorithms on personal devices. Yet, they still face an important challenge, that of long-term structure, which is key to conveying a sense of musical coher...
Digital advances have transformed the face of automatic music generation since its beginnings at the dawn of computing. Despite the many breakthroughs, issues such as the musical tasks targeted by different machines and the degree to which they succeed remain open questions. We present a functional taxonomy for music generation systems with referen...
We propose an end-to-end approach for modeling polyphonic music with a novel graphical representation, based on music theory, in a deep neural network. Despite the success of deep learning in various applications, it remains a challenge to incorporate existing domain knowledge in a network without affecting its training routines. In this paper we p...
A total of 34% of AI research and development projects fail or are abandoned, according to a recent survey by Rackspace Technology of 1,870 companies [1]. In this perspective paper, a new STrategic ROadMap, aiSTROM, is presented that empowers managers to create an AI strategy. A comprehensive approach is provided that guides managers and lead devel...
This paper introduces text2midi, an end-to-end model to generate MIDI files from textual descriptions. Leveraging the growing popularity of multimodal generative approaches, text2midi capitalizes on the extensive availability of textual data and the success of large language models (LLMs). Our end-to-end system harnesses the power of LLMs to genera...
We introduce JamendoMaxCaps, a large-scale music-caption dataset featuring over 200,000 freely licensed instrumental tracks from the renowned Jamendo platform. The dataset includes captions generated by a state-of-the-art captioning model, enhanced with imputed metadata. We also introduce a retrieval system that leverages both musical features and...
One of the most significant challenges in Music Emotion Recognition (MER) comes from the fact that emotion labels can be heterogeneous across datasets with regard to the emotion representation, including categorical (e.g., happy, sad) versus dimensional labels (e.g., valence-arousal). In this paper, we present a unified multitask learning framework...
Deep learning has enabled remarkable advances in style transfer across various domains, offering new possibilities for creative content generation. However, in the realm of symbolic music, generating controllable and expressive performance-level style transfers for complete musical works remains challenging due to limited datasets, especially for g...
Music is frequently associated with the notion of language as both domains share several similarities, including the ability for their content to be represented as sequences of symbols. In computer science, the fields of Natural Language Processing (NLP) and Music Information Retrieval (MIR) reflect this analogy through a variety of similar tasks,...
Current strategies for achieving fine-grained prosody control in speech synthesis entail extracting additional style embeddings or adopting more complex architectures. To enable zero-shot application of pretrained text-to-speech (TTS) models, we present PRESENT (PRosody Editing without Style Embeddings or New Training), which exploits explicit pros...
This study uses a transformer model to enhance the controllability of generative symbolic music models, specifically related to the infilling task.We introduce a novel Symbolic Music representation with Explicit Rest notation (SMER) encoding incorporating five basic duration types and explicit rest note tokens similar to standard music notation. We...
This paper introduces text2midi, an end-to-end model to generate MIDI files from textual descriptions. Leveraging the growing popularity of multimodal generative approaches, text2midi capitalizes on the extensive availability of textual data and the success of large language models (LLMs). Our end-to-end system harnesses the power of LLMs to genera...
This paper introduces an extendable modular system that compiles a range of music feature extraction models to aid music information retrieval research. The features include musical elements like key, downbeats, and genre, as well as audio characteristics like instrument recognition, vocals/instrumental classification, and vocals gender detection....
Recent advancements in Text-to-Speech (TTS) systems have enabled the generation of natural and expressive speech from textual input. Accented TTS aims to enhance user experience by making the synthesized speech more relatable to minority group listeners, and useful across various applications and context. Speech synthesis can further be made more f...
In this work, we present a novel method for music emotion recognition that leverages Large Language Model (LLM) embeddings for label alignment across multiple datasets and zero-shot prediction on novel categories. First, we compute LLM embeddings for emotion labels and apply non-parametric clustering to group similar labels, across multiple dataset...
In tandem with the recent advancements in foundation model research, there has been a surge of generative music AI applications within the past few years. As the idea of AI-generated or AI-augmented music becomes more mainstream, many researchers in the music AI community may be wondering what avenues of research are left. With regards to music gen...
Current strategies for achieving fine-grained prosody control in speech synthesis entail extracting additional style embeddings or adopting more complex architectures. To enable zero-shot application of pretrained text-to-speech (TTS) models, we present PRESENT (PRosody Editing without Style Embeddings or New Training), which exploits explicit pros...
Controllable music generation promotes the interaction between humans and composition systems by projecting the users' intent on their desired music. The challenge of introducing controllability is an increasingly important issue in the symbolic music generation field. When building controllable generative popular multi-instrument music systems, tw...
Laughing, sighing, stuttering, and other forms of paralanguage do not contribute any direct lexical meaning to speech, but they provide crucial propositional context that aids semantic and pragmatic processes such as irony. It is thus important for artificial social agents to both understand and be able to generate speech with semantically-importan...
Deep learning models for music have advanced drastically in the last few years. But how good are machine learning models at capturing emotion these days and what challenges are researchers facing? In this paper, we provide a comprehensive overview of the available music-emotion datasets and discuss evaluation standards as well as competitions in th...
This paper introduces DeepUnifiedMom, a deep learning framework that enhances portfolio management through a multi-task learning approach and a multi-gate mixture of experts. The essence of DeepUnifiedMom lies in its ability to create unified momentum portfolios that incorporate the dynamics of time series momentum across a spectrum of time frames,...
Generative models guided by text prompts are increasingly becoming more popular. However, no text-to-MIDI models currently exist, mostly due to the lack of a captioned MIDI dataset. This work aims to enable research that combines LLMs with symbolic music by presenting the first large-scale MIDI dataset with text captions that is openly available: M...
The quality of the text-to-music models has reached new heights due to recent advancements in diffusion models. The controllabil-ity of various musical aspects, however, has barely been explored. In this paper, we propose Mustango: a music-domain-knowledge-inspired text-to-music system based on diffusion. Mustango aims to control the generated musi...
Following the success of the transformer architecture in the natural language domain, transformer-like architectures have been widely applied to the domain of symbolic music recently. Symbolic music and text, however, are two different modalities. Symbolic music contains multiple attributes, both absolute attributes (e.g., pitch) and relative attri...
A diversified risk-adjusted time-series momentum (TSMOM) portfolio can deliver substantial abnormal returns and offer some degree of tail risk protection during extreme market events. The performance of existing TSMOM strategies, however, relies not only on the quality of the momentum signal but also on the efficacy of the volatility estimator. Yet...
In this paper, we introduce Jointist, an instrument-aware multi-instrument framework that is capable of transcribing, recognizing, and separating multiple musical instruments from an audio clip. Jointist consists of an instrument recognition module that conditions the other two modules: a transcription module that outputs instrument-specific piano...
Music is capable of conveying many emotions. The level and type of emotion of the music perceived by a listener, however, is highly subjective. In this study, we present the Music Emotion Recognition with Profile information dataset (MERP). This database was collected through Amazon Mechanical Turk (MTurk) and features dynamical valence and arousal...
An audio-based classification model that differentiates between healthy vs pathological respiratory symptoms using acoustic features extracted from phonated /ɑː/ sounds is presented. For this, a new dataset of phonated /ɑː/ sounds, together with a clinician’s diagnosis, was compiled and a Gaussian Mixture Model (GMM) using Mel-Frequency Cepstral Co...
Following the success of the transformer architecture in the natural language domain, transformer-like architectures have been widely applied to the domain of symbolic music recently. Symbolic music and text, however, are two different modalities. Symbolic music contains multiple attributes, both absolute attributes (e.g., pitch) and relative attri...
Text-to-speech (TTS) models have achieved remarkable naturalness in recent years, yet like most deep neural models, they have more parameters than necessary. Sparse TTS models can improve on dense models via pruning and extra retraining, or converge faster than dense models with some performance loss. Inspired by these results, we propose training...
Accent plays a significant role in speech communication, influencing understanding capabilities and also conveying a person's identity. This paper introduces a novel and efficient framework for accented Text-to-Speech (TTS) synthesis based on a Conditional Variational Autoencoder. It has the ability to synthesize a selected speaker's speech that is...
This paper puts forth a method that is easily transposable to a
realtime environment by utilising a “Physics Approximating Neural
Network" to predict 1D output signal. The technique described in
this paper is inspired by Physics Informed Neural Networks put
forth by Raissi et al. The model demonstrated in this paper makes
use of a recurrent input....
Music is capable of conveying many emotions. The level and type of emotion of the music perceived by a listener, however, is highly subjective. In this study, we present the Music Emotion Recognition with Profile information dataset (MERP). This database was collected through Amazon Mechanical Turk (MTurk) and features dynamical valence and arousal...
Accent is a crucial aspect of speech that helps define one's identity. We note that the state-of-the-art Text-to-Speech (TTS) systems can achieve high-quality generated voice, but still lack in terms of versatility and customizability. Moreover , they generally do not take into account accent, which is an important feature of speaking style. In thi...
In this paper we propose a novel generative approach, DiffRoll, to tackle automatic music transcription (AMT). Instead of treating AMT as a discriminative task in which the model is trained to convert spectrograms into piano rolls, we think of it as a conditional generative task where we train our model to generate realistic looking piano rolls fro...
The cryptocurrency market is highly volatile compared to traditional financial markets. Hence, forecasting its volatility is crucial for risk management. In this paper, we investigate CryptoQuant data (e.g. on-chain analytics, exchange and miner data) and whale-alert tweets, and explore their relationship to Bitcoin's next-day volatility, with a fo...
Studies in affective audio–visual correspondence learning require ground-truth data to train, validate, and test models. The number of available datasets together with benchmarks, however, is still limited. In this paper, we create a collection of three datasets (called EmoMV) for affective correspondence learning between music and video modalities...
Inspired by recent advancements in the field of computer vision, specifically models for generating higher-resolution images from low-resolution images, we investigate the utility of a deep convolutional autoencoder for downscaling and bias correcting climate projections for South East Asia (SEA). Downscaled projections of 2 m surface temperature a...
In this paper, we introduce Jointist, an instrument-aware multi-instrument framework that is capable of transcribing, recognizing, and separating multiple musical instruments from an audio clip. Jointist consists of the instrument recognition module that conditions the other modules: the transcription module that outputs instrument-specific piano r...
Guitar tablature transcription consists in deducing the string and the fret number on which each note should be played to reproduce the actual musical part. This assignment should lead to playable string-fret combinations throughout the entire track and, in general, preserve parsimonious motion between successive combinations. Throughout the histor...
Bitcoin, with its ever-growing popularity, has demonstrated extreme price volatility since its origin. This volatility, together with its decentralised nature, make Bitcoin highly subjective to speculative trading as compared to more traditional assets. In this paper, we propose a multimodal model for predicting extreme price fluctuations. This mod...
In this paper, we introduce an approach for future frames prediction based on a single input image. Our method is able to generate an entire video sequence based on the information contained in the input frame. We adopt an autoregressive approach in our generation process, i.e., the output from each time step is fed as the input to the next step. U...
In this paper we explore the possibility of maximizing the information represented in spectrograms by making the spectrogram basis functions trainable. We experiment with two different tasks, namely keyword spotting (KWS) and automatic speech recognition (ASR). For most neural network models, the architecture and hyperparameters are typically fine-...
The field of automatic music composition has seen great progress in recent years, specifically with the invention of transformer-based architectures. When using any deep learning model which considers music as a sequence of events with multiple complex dependencies, the selection of a proper data representation is crucial. In this paper, we tackle...
We present a novel music generation framework for music infilling, with a user friendly interface. Infilling refers to the task of generating musical sections given the surrounding multi-track music. The proposed transformer-based framework is extensible for new control tokens as the added music control tokens such as tonal tension per bar and trac...
What audio embedding approach generalizes best to a wide range of downstream tasks across a variety of everyday domains without fine-tuning? The aim of the HEAR 2021 NeurIPS challenge is to develop a general-purpose audio representation that provides a strong basis for learning in a wide variety of tasks and scenarios. HEAR 2021 evaluates audio rep...
Although media content is increasingly produced, distributed, and consumed in multiple combinations of modalities, how individual modalities contribute to the perceived emotion of a media item remains poorly understood. In this paper we present MusicVideos (MuVi), a novel dataset for affective multimedia content analysis to study how the auditory a...
We present a novel music generation framework for music infilling, with a user friendly interface. Infilling refers to the task of generating musical sections given the surrounding multi-track music. The proposed transformer-based framework is extensible for new control tokens as the added music control tokens such as tonal tension per bar and trac...
The field of automatic music composition has seen great progress in recent years, specifically with the invention of transformer-based architectures. When using any deep learning model which considers music as a sequence of events with multiple complex dependencies, the selection of a proper data representation is crucial. In this paper, we tackle...
While public awareness of climate change has grown over the years, many people still have misconceptions regarding effective individual environmental action. In this paper, we present a serious game called PEAR, developed using elements of geolocation and augmented reality (AR), aimed at increasing players’ awareness of climate change issues and pr...
In this paper, we tackle the problem of predicting the affective responses of movie viewers, based on the content of the movies. Current studies on this topic focus on video representation learning and fusion techniques to combine the extracted features for predicting affect. Yet, these typically, while ignoring the correlation between multiple mod...
Intelligent systems are transforming the world, as well as our healthcare system. We propose a deep learning-based cough sound classification model that can distinguish between children with healthy versus pathological coughs such as asthma, upper respiratory tract infection (URTI), and lower respiratory tract infection (LRTI). To train a deep neur...
Most of the current supervised automatic music transcription (AMT) models lack the ability to generalize. This means that they have trouble transcribing real-world music recordings from diverse musical genres that are not presented in the labelled training data. In this paper, we propose a semi-supervised framework, ReconVAT, which solves this issu...
A total of 34% of AI research and development projects fails or are abandoned, according to a recent survey by Rackspace Technology of 1,870 companies. We propose a new strategic framework, aiSTROM, that empowers managers to create a successful AI strategy based on a thorough literature review. This provides a unique and integrated approach that gu...
Intelligent systems are transforming the world, as well as our healthcare system. We propose a deep learning-based cough sound classification model that can distinguish between children with healthy versus pathological coughs such as asthma, upper respiratory tract infection (URTI), and lower respiratory tract infection (LRTI). In order to train a...
The fields of music, health, and technology have seen significant interactions in recent years in developing music technology for health care and well-being. In an effort to strengthen the collaboration between the involved disciplines, the workshop “Music, Computing, and Health” was held to discuss best practices and state-of-the-art at the inters...
Recent advances in automatic music transcription (AMT) have achieved highly accurate polyphonic piano transcription results by incorporating onset and offset detection. The existing literature, however, focuses mainly on the leverage of deep and complex models to achieve state-of-the-art (SOTA) accuracy, without understanding model behaviour. In th...
The field of automatic music composition has seen great progress in the last few years, much of which can be attributed to advances in deep neural networks. There are numerous studies that present different strategies for generating sheet music from scratch. The inclusion of high-level musical characteristics (e.g., perceived emotional qualities),...
The rise of deep learning technologies has quickly advanced many fields, including generative music systems. There exists a number of systems that allow for the generation of musically sounding short snippets, yet, these generated snippets often lack an overarching, longer-term structure. In this work, we propose CM-HRNN: a conditional melody gener...
The field of automatic music composition has seen great progress in the last few years, much of which can be attributed to advances in deep neural networks. There are numerous studies that present different strategies for generating sheet music from scratch. The inclusion of high-level musical characteristics (e.g., perceived emotional qualities),...
Recent advances in automatic music transcription (AMT) have achieved highly accurate polyphonic piano transcription results by incorporating onset and offset detection. The existing literature, however, focuses mainly on the leverage of deep and complex models to achieve state-of-the-art (SOTA) accuracy, without understanding model behaviour. In th...
Underwater environments create a challenging channel for communications. In this paper, we design a novel receiver system by exploring the machine learning technique–Deep Belief Network (DBN) – to combat the signal distortion caused by the Doppler effect and multi-path propagation. We evaluate the performance of the proposed receiver system in both...
Underwater environments create a challenging channel for communications. In this paper, we design a novel receiver system by exploring the machine learning technique--Deep Belief Network (DBN)-- to combat the signal distortion caused by the Doppler effect and multi-path propagation. We evaluate the performance of the proposed receiver system in bot...
The fields of music, health, and technology have seen significant interactions in recent years in developing music technology for health care and well-being. In an effort to strengthen the collaboration between the involved disciplines, the workshop ‘Music, Computing, and Health’ was held to discuss best practices and state-of-the-art at the inters...
The rise of deep learning technologies has quickly advanced many fields, including that of generative music systems. There exist a number of systems that allow for the generation of good sounding short snippets, yet, these generated snippets often lack an overarching, longer-term structure. In this work, we propose CM-HRNN: a conditional melody gen...
In this work, we propose different variants of the self-attention based network for emotion prediction from movies, which we call AttendAffectNet. We take both audio and video into account and incorporate the relation among multiple modalities by applying self-attention mechanism in a novel manner into the extracted features for emotion prediction....
Most of the state-of-the-art automatic music transcription (AMT) models break down the main transcription task into sub-tasks such as onset prediction and offset prediction and train them with onset and offset labels. These predictions are then concatenated together and used as the input to train another model with the pitch labels to obtain the fi...
In this work, we propose different variants of the self-attention based network for emotion prediction from movies, which we call AttendAffectNet. We take both audio and video into account and incorporate the relation among multiple modalities by applying self-attention mechanism in a novel manner into the extracted features for emotion prediction....
Most of the state-of-the-art automatic music transcription (AMT) models break down the main transcription task into sub-tasks such as onset prediction and offset prediction and train them with onset and offset labels. These predictions are then concatenated together and used as the input to train another model with the pitch labels to obtain the fi...
Billions of USD are invested in new artists and songs by the music industry every year. This research provides a new strategy for assessing the hit potential of songs, which can help record companies support their investment decisions. A number of models were developed that use both audio data, and a novel feature based on social media listening be...
Many of the music generation systems based on neural networks are fully autonomous and do not offer control over the generation process. In this research, we present a controllable music generation system in terms of tonal tension. We incorporate two tonal tension measures based on the Spiral Array Tension theory into a variational autoencoder mode...
In this paper we present a new dataset, with musical excepts from the three main ethnic groups in Singapore: Chinese, Malay and Indian (both Hindi and Tamil). We use this new dataset to train different classification models to distinguish the origin of the music in terms of these ethnic groups. The classification models were optimized by exploring...
In this paper, we present nnAudio, a new neural network-based audio processing framework with graphics processing unit (GPU) support that leverages 1D convolutional neural networks to perform time domain to frequency domain conversion. It allows on-the-fly spectrogram extraction due to its fast speed, without the need to store any spectrograms on t...
High-level musical qualities (such as emotion) are often abstract, subjective, and hard to quantify. Given these difficulties, it is not easy to learn good feature representations with supervised learning techniques, either because of the insufficiency of labels, or the subjectiveness (and hence large variance) in human-annotated labels. In this pa...
We present a controllable neural audio synthesizer based on Gaussian Mixture Variational Autoencoders (GM-VAE), which can generate realistic piano performances in the audio domain that closely follows temporal conditions of two essential style features for piano performances: articulation and dynamics. We demonstrate how the model is able to apply...
Cough is a common symptom presenting in asthmatic children. In this investigation, an audio-based classification model is presented that can differentiate between healthy and asthmatic children, based on the combination of cough and vocalised /ɑ:/ sounds. A Gaussian mixture model using mel-frequency cepstral coefficients and constant-Q cepstral coe...
High-level musical qualities (such as emotion) are often abstract, subjective, and hard to quantify. Given these difficulties, it is not easy to learn good feature representations with supervised learning techniques, either because of the insufficiency of labels, or the subjectiveness (and hence large variance) in human-annotated labels. In this pa...
In this paper, we adapt triplet neural networks (TNNs) to a regression task, music emotion prediction. Since TNNs were initially introduced for classification, and not for regression, we propose a mechanism that allows them to provide meaningful low dimensional representations for regression tasks. We then use these new representations as the input...
Generating an image from a provided descriptive text is quite a challenging task because of the difficulty in incorporating perceptual information (object shapes, colors, and their interactions) along with providing high relevancy related to the provided text. Current methods first generate an initial low-resolution image, which typically has irreg...
Generating an image from a provided descriptive text is quite a challenging task because of the difficulty in incorporating perceptual information (object shapes, colors, and their interactions) along with providing high relevancy related to the provided text. Current methods first generate an initial low-resolution image, which typically has irreg...