Tuomas Virtanen

• Tampere University

Music source separation is the task of separating a mixture of instruments into constituent tracks. Music source separation models are typically trained using only audio data, although additional information can be used to improve the model's separation capability. In this paper, we propose two ways of using musical scores to aid music source separ...

In this work, we investigate the generalization of a multi-channel learning-based replay speech detector, which employs adaptive beamforming and detection, across different microphone arrays. In general, deep neural network-based microphone array processing techniques generalize poorly to unseen array types, i.e., showing a significant training-tes...

Replay attacks belong to the class of severe threats against voice-controlled systems, exploiting the easy accessibility of speech signals by recorded and replayed speech to grant unauthorized access to sensitive data. In this work, we propose a multi-channel neural network architecture called M-ALRAD for the detection of replay attacks based on sp...

Accurate labels are critical for deriving robust machine learning models. Labels are used to train supervised learning models and to evaluate most machine learning paradigms. In this paper, we model the accuracy and cost of a common weak labeling process where annotators assign presence or absence labels to fixed-length data segments for a given ev...

Using deep neural networks (DNNs) for encoding of microphone array (MA) signals to the Ambisonics spatial audio format can surpass certain limitations of established conventional methods, but existing DNN-based methods need to be trained separately for each MA. This paper proposes a DNN-based method for Ambisonics encoding that can generalize to ar...

This paper studies the novel problem of automatic live music song identification, where the goal is, given a live recording of a song, to retrieve the corresponding studio version of the song from a music database. We propose a system based on similarity learning and a Siamese convolutional neural network-based model. The model uses cross-similarit...

Recent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks. These developments owe much to the creation and use of large-scale, multitrack datasets dedicated to these specific components. However, the challenge of extracting similarly sounding sources fr...

This paper proposes to use similarities of audio captions for estimating audio-caption relevances to be used for training text-based audio retrieval systems. Current audio-caption datasets (e.g., Clotho) contain audio samples paired with annotated captions, but lack relevance information about audio samples and captions beyond the annotated ones. B...

The Rosanna shuffle, the drum pattern from Toto's 1982 hit "Rosanna", is one of the most recognized drum beats in popular music. Recorded by Jeff Porcaro, this drum beat features a half-time shuffle with rapid triplets on the hi-hat and snare drum. In this analysis, we examine the timing and dynamics of the original drum track, focusing on rhythmic...

This paper introduces briefly the history and growth of the Detection and Classification of Acoustic Scenes and Events (DCASE) challenge, workshop, research area and research community. Created in 2013 as a data evaluation challenge, DCASE has become a major research topic in the Audio and Acoustic Signal Processing area. Its success comes from a c...

Recent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks. These developments owe much to the creation and use of large-scale, multitrack datasets dedicated to these specific components. However, the challenge of extracting similarly sounding sources fr...

Audio-text relevance learning refers to learning the shared semantic properties of audio samples and textual descriptions. The standard approach uses binary relevances derived from pairs of audio samples and their human-provided captions, categorizing each pair as either positive or negative. This may result in suboptimal systems due to varying lev...

In end-to-end multi-channel speech enhancement, the traditional approach of designating one microphone signal as the reference for processing may not always yield optimal results. The limitation is particularly in scenarios with large distributed microphone arrays with varying speaker-to-microphone distances or compact, highly directional microphon...

Distance estimation from audio plays a crucial role in various applications, such as acoustic scene analysis, sound source localization, and room modeling. Most studies predominantly center on employing a classification approach, where distances are discretized into distinct categories, enabling smoother model training and achieving higher accuracy...

Sound event detection systems are widely used in various applications such as surveillance and environmental monitoring where data is automatically collected, processed, and sent to a cloud for sound recognition. However, this process may inadvertently reveal sensitive information about users or their surroundings, hence raising privacy concerns. I...

This paper proposes to use similarities of audio captions for estimating audio-caption relevances to be used for training text-based audio retrieval systems. Current audio-caption datasets (e.g., Clotho) contain audio samples paired with annotated captions, but lack relevance information about audio samples and captions beyond the annotated ones. B...

Current multichannel speech enhancement algorithms typically assume a stationary sound source, a common mismatch with reality that limits their performance in real-world scenarios. This paper focuses on attention-driven spatial filtering techniques designed for dynamic settings. Specifically, we study the application of linear and nonlinear attenti...

We introduce the novel task of continuous-valued speaker distance estimation which focuses on estimating non-discrete distances between a sound source and microphone, based on audio captured by the microphone. A novel learning-based approach for estimating speaker distance in reverberant environments from a single omnidi-rectional microphone is pro...

Distance estimation from audio plays a crucial role in various applications, such as acoustic scene analysis, sound source localization, and room modeling. Most studies predominantly center on employing a classification approach, where distances are discretized into distinct categories, enabling smoother model training and achieving higher accuracy...

Privacy preservation has long been a concern in smart acoustic monitoring systems, where speech can be passively recorded along with a target signal in the system's operating environment. In this study, we propose the integration of two commonly used approaches in privacy preservation: source separation and adversarial representation learning. The...

This paper explores grading text-based audio retrieval relevances with crowdsourcing assessments. Given a free-form text (e.g., a caption) as a query, crowdworkers are asked to grade audio clips using numeric scores (between 0 and 100) to indicate their judgements of how much the sound content of an audio clip matches the text, where 0 indicates no...

While direction of arrival (DOA) of sound events is generally estimated from multichannel audio data recorded in a microphone array, sound events usually derive from visually perceptible source objects, e.g., sounds of footsteps come from the feet of a walker. This paper proposes an audio-visual sound event localization and detection (SELD) task, w...

Many multi-source localization and tracking models based on neural networks use one or several recurrent layers at their final stages to track the movement of the sources. Conventional recurrent neural networks (RNNs), such as the long short-term memories (LSTMs) or the gated recurrent units (GRUs), take a vector as their input and use another vect...

Speech representation learning with self-supervised algorithms has resulted in notable performance boosts in many downstream tasks. Recent work combined self-supervised learning (SSL) and visually grounded speech (VGS) processing mechanisms for representation learning. The joint training with SSL and VGS mechanisms provides the opportunity to utili...

Audio question answering (AQA) is the task of producing natural language answers when a system is provided with audio and natural language questions. In this paper, we propose neural network architectures based on self-attention and cross-attention for the AQA task. The self-attention layers extract powerful audio and textual representations. The c...

New classes of sounds constantly emerge with a few samples, making it challenging for models to adapt to dynamic acoustic environments. This challenge motivates us to address the new problem of few-shot class-incremental audio classification. This study aims to enable a model to continuously recognize new classes of sounds with a few training sampl...

Sound event detection systems are widely used in various applications such as surveillance and environmental monitoring where data is automatically collected, processed, and sent to a cloud for sound recognition. However, this process may inadvertently reveal sensitive information about users or their surroundings, hence raising privacy concerns. I...

Audio source separation is often achieved by estimating the magnitude spectrogram of each source, and then applying a phase recovery (or spectrogram inversion) algorithm to retrieve time-domain signals. Typically, spectrogram inversion is treated as an optimization problem involving one or several terms in order to promote estimates that comply wit...

Research work on automatic speech recognition and automatic music transcription has been around for several decades, supported by dedicated conferences or conference sessions. However, while individual researchers have been working on recognition of more general environmental sounds, until ten years ago there were no regular workshops or conference...

This paper proposes neural networks for compensating sensorineural hearing loss. The aim of the hearing loss compensation task is to transform a speech signal to increase speech intelligibility after further processing by a person with a hearing impairment, which is modeled by a hearing loss model. We propose an interpretable model called dynamic p...

This paper investigates negative sampling for contrastive learning in the context of audio-text retrieval. The strategy for negative sampling refers to selecting negatives (either audio clips or textual descriptions) from a pool of candidates for a positive audio-text pair. We explore sampling strategies via model-estimated within-modality and cros...

Recent data- and learning-based sound source localization (SSL) methods have shown strong performance in challenging acoustic scenarios. However, little work has been done on adapting such methods to track consistently multiple sources appearing and disappearing, as would occur in reality. In this paper, we present a new training strategy for deep...

Learning from audio-visual data offers many possibilities to express correspondence between the audio and visual content, similar to the human perception that relates aural and visual information. In this work, we present a method for self-supervised representation learning based on audio-visual spatial alignment (AVSA), a more sophisticated alignm...

Language-based audio retrieval is a task, where natural language textual captions are used as queries to retrieve audio signals from a dataset. It has been first introduced into DCASE 2022 Challenge as Subtask 6B of task 6, which aims at developing computational systems to model relationships between audio signals and free-form textual descriptions...

Subjective evaluation results for two low-latency deep neural networks (DNN) are compared to a matured version of a traditional Wiener-filter based noise suppressor. The target use-case is real-world single-channel speech enhancement applications, e.g., communications. Real-world recordings consisting of additive stationary and non-stationary noise...

Automatic estimation of domestic activities from audio can be used to solve many problems, such as reducing the labor cost for nursing the elderly people. This study focuses on solving the problem of domestic activity clustering from audio. The target of domestic activity clustering is to cluster audio clips which belong to the same category of dom...

In this report, we introduce the task setup and the baseline system for the sub-task B of the DCASE 2022 Challenge Task 6: language-based audio retrieval subtask. For this subtask, the Clotho v2 dataset is utilized as the development dataset, and an additional dataset consisting of 1,000 audio-caption pairs as the evaluation dataset. We train the b...

Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and time-consuming. Zero-shot learning models are capable of classifying the unseen concepts by utilizing their semantic i...

This paper analyzes the outcome of the Low-Complexity Acoustic Scene Classification task in DCASE 2022 Challenge. The task is a continuation from the previous years. In this edition, the requirement for low-complexity solutions were modified including: a limit of 128 K on the number of parameters, including the zero-valued ones, imposed INT8 numeri...

This report presents the Sony-TAu Realistic Spatial Soundscapes 2022 (STARS22) dataset for sound event localization and detection, comprised of spatial recordings of real scenes collected in various interiors of two different sites. The dataset is captured with a high resolution spherical microphone array and delivered in two 4-channel formats, fir...

Learning from audio-visual data offers many possibilities to express correspondence between the audio and visual content, similar to the human perception that relates aural and visual information. In this work, we present a method for self-supervised representation learning based on audio-visual spatial alignment (AVSA), a more sophisticated alignm...

Audio question answering (AQA) is a multimodal translation task where a system analyzes an audio signal and a natural language question, to generate a desirable natural language answer. In this paper, we introduce Clotho-AQA, a dataset for Audio question answering consisting of 1991 audio files each between 15 to 30 seconds in duration selected fro...

COVID-19 infection’s recent outbreak triggered by the SARS-CoV-2 Corona virus had already led to more than two million reported infected individuals when we first addressed the community by our call – by now, the number sadly rose to roughly half a billion cases worldwide. The outbreak of COIVD-19 has also re-shaped and accelerated the scientific p...

Data-based and learning-based sound source localization (SSL) has shown promising results in challenging conditions, and is commonly set as a classification or a regression problem. Regression-based approaches have certain advantages over classification-based, such as continuous direction-of-arrival estimation of static and moving sources. However,...

We investigate unsupervised learning of correspondences between sound events and textual phrases through aligning audio clips with textual captions describing the content of a whole audio clip. We align originally unaligned and unannotated audio clips and their captions by scoring the similarities between audio frames and words, as encoded by modal...

The paper addresses acoustic vehicle speed estimation using single sensor measurements. We introduce a new speed-dependent feature based on the attenuation of the sound amplitude. The feature is predicted from the audio signal and used as input to a regression model for speed estimation. For this research, we have collected, annotated, and publishe...

Joint sound event localization and detection (SELD) is an integral part of developing context awareness into communication interfaces of mobile robots, smartphones, and home assistants. For example, an automatic audio focus for video capture on a mobile phone requires robust detection of relevant acoustic events around the device and their directio...

Imagine standing on a street corner in the city. With your eyes closed you can hear and recognize a succession of sounds: cars passing by, people speaking, their footsteps when they walk by, and the continuous falling of rain. The recognition of all these sounds and interpretation of the perceived scene as a city street soundscape comes naturally t...

The goal of automatic sound event detection (SED) methods is to recognize what is happening in an audio signal and when it is happening. In practice, the goal is to recognize at what temporal instances different sounds are active within an audio signal. This paper gives a tutorial presentation of sound event detection, including its definition, sig...

Joint sound event localization and detection (SELD) is an integral part of developing context awareness into communication interfaces of mobile robots, smartphones, and home assistants. For example, an automatic audio focus for video capture on a mobile phone requires robust detection of relevant acoustic events around the device and their directio...

Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper, we propose the usage of an asymmetric analysis-synthesis window pair which allows for training with targets with better frequency resolution, while retaining the low-la...

This report presents the dataset and baseline of Task 3 of the DCASE2021 Challenge on Sound Event Localization and Detection (SELD). The dataset is based on emulation of real recordings of static or moving sound events under real conditions of reverberation and ambient noise, using spatial room impulse responses captured in a variety of rooms and d...

This paper presents the details of the Audio-Visual Scene Classification task in the DCASE 2021 Challenge (Task 1 Subtask B). The task is concerned with classification using audio and video modalities, using a dataset of synchronized recordings. This task has attracted 43 submissions from 13 different teams around the world. Among all submissions,...

This paper presents the details of Task 1A Acoustic Scene Classification in the DCASE 2021 Challenge. The task consisted of classification of data from multiple devices, requiring good generalization properties, using low-complexity solutions. The provided baseline system is based on a CNN architecture and post-training parameters quantization. The...

In this article, we propose a new method for joint cochannel speaker separation and recognition called adaptive-dictionary non-negative matrix deconvolution (DANMD). This method is an extension of non-negative matrix deconvolution (NMD) which models spectrogram matrix as a linear combination of dictionary elements (atoms). We propose a dictionary w...

In this paper, we study zero-shot learning in audio classification via semantic embeddings extracted from textual labels and sentence descriptions of sound classes. Our goal is to obtain a classifier that is capable of recognizing audio instances of sound classes that have no available training samples, but only semantic side information. We employ...

Sound event localization and detection is a novel area of research that emerged from the combined interest of analyzing the acoustic scene in terms of the spatial and temporal activity of sounds of interest. This paper presents an overview of the first international evaluation on sound event localization and detection, organized as a task of the DC...

In this paper, we study zero-shot learning in audio classification through factored linear and nonlinear acoustic-semantic projections between audio instances and sound classes. Zero-shot learning in audio classification refers to classification problems that aim at recognizing audio instances of sound classes, which have no available training data...

In this paper, we study zero-shot learning in audio classification via semantic embeddings extracted from textual labels and sentence descriptions of sound classes. Our goal is to obtain a classifier that is capable of recognizing audio instances of sound classes that have no available training samples, but only semantic side information. We employ...

This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from which it selects sound segments for manual annotation. The candidate segments are generated based on a propos...

This paper introduces a curated dataset of urban scenes for audio-visual scene analysis which consists of carefully selected and recorded material. The data was recorded in multiple European cities, using the same equipment, in multiple locations for each scene, and is openly available. We also present a case study for audio-visual scene recognitio...

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags associated with audio do not employ text processing models that are capable to generalize to tags unknown during tra...

This paper addresses acoustic vehicle counting using one-channel audio. We predict the pass-by instants of vehicles from local minima of a vehicle-to-microphone distance predicted from audio. The distance is predicted via a two-stage (coarse-fine) regression, both realised using neural networks (NNs). Experiments show that the NN-based distance reg...

The paper presents a method for audio-based vehicle counting (VC) in low-to-moderate traffic using one-channel sound. We formulate VC as a regression problem, i.e., we predict the distance between a vehicle and the microphone. Minima of the proposed distance function correspond to vehicles passing by the microphone. VC is carried out via local mini...

Automated audio captioning (AAC) is a novel task, where a method takes as an input an audio sample and outputs a textual description (i.e. a caption) of its contents. Most AAC methods are adapted from from image captioning of machine translation fields. In this work we present a novel AAC novel method, explicitly focused on the exploitation of the...

It has been suggested that early cry parameters are connected to later cognitive abilities. The present study is the first to investigate whether the acoustic features of infant cry are associated with cognitive development already during the first year, as measured by oculomotor orienting and attention disengagement. Cry sounds for acoustic analys...

Sound event localization and detection is a novel area of research that emerged from the combined interest of analyzing the acoustic scene in terms of the spatial and temporal activity of sounds of interest. This paper presents an overview of the first international evaluation on sound event localization and detection, organized as a task of DCASE...