859 citations · 3.5k across the 72 of their papers we have counts for
87 papers
Multi-label Zero-Shot Audio Classification with Temporal Attention
Duygu Dogan, Huang Xie, Toni Heittola +1
Zero-shot learning models are capable of classifying new classes by transferring knowledge from the seen classes using auxiliary information. While most of the existing zero-shot l…
Integrating Continuous and Binary Relevances in Audio-Text Relevance Learning
Huang Xie, Khazar Khorrami, Okko Räsänen +1
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…
Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning
Diep Luong, Minh Tran, Shayan Gharib +2
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 envir…
Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications
David Diaz-Guerra, Archontis Politis, Antonio Miguel +2
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. Conventi…
Simultaneous or Sequential Training? How Speech Representations Cooperate in a Multi-Task Self-Supervised Learning System
Khazar Khorrami, María Andrea Cruz Blandón, Tuomas Virtanen +1
Speech representation learning with self-supervised algorithms has resulted in notable performance boosts in many downstream tasks. Recent work combined self-supervised learning (S…
Crowdsourcing and Evaluating Text-Based Audio Retrieval Relevances
Huang Xie, Khazar Khorrami, Okko Räsänen +1
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 gra…
STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events
Kazuki Shimada, Archontis Politis, Parthasaarathy Sudarsanam +9
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 perce…
Attention-Based Methods For Audio Question Answering
Parthasaarathy Sudarsanam, Tuomas Virtanen
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 neur…
Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypes
Wei Xie, Yanxiong Li, Qianhua He +2
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 n…
Adversarial Representation Learning for Robust Privacy Preservation in Audio
Shayan Gharib, Minh Tran, Diep Luong +2
Sound event detection systems are widely used in various applications such as surveillance and environmental monitoring where data is automatically collected, processed, and sent t…
Multi-Channel Masking with Learnable Filterbank for Sound Source Separation
Wang Dai, Archontis Politis, Tuomas Virtanen
This work proposes a learnable filterbank based on a multi-channel masking framework for multi-channel source separation. The learnable filterbank is a 1D Conv layer, which transfo…
Spectrogram Inversion for Audio Source Separation via Consistency, Mixing, and Magnitude Constraints
Paul Magron, Tuomas Virtanen
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 retriev…
On Negative Sampling for Contrastive Audio-Text Retrieval
Huang Xie, Okko Räsänen, Tuomas Virtanen
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…
Language-based Audio Retrieval Task in DCASE 2022 Challenge
Huang Xie, Samuel Lipping, Tuomas Virtanen
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 DC…
Position tracking of a varying number of sound sources with sliding permutation invariant training
David Diaz-Guerra, Archontis Politis, Tuomas Virtanen
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 adapt…
Subjective Evaluation of Deep Neural Network Based Speech Enhancement Systems in Real-World Conditions
Gaurav Naithani, Kirsi Pietilä, Riitta Niemistö +3
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…
Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network
Yanxiong Li, Wenchang Cao, Konstantinos Drossos +1
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 sol…
Low-complexity acoustic scene classification in DCASE 2022 Challenge
Irene Martín-Morató, Francesco Paissan, Alberto Ancilotto +5
This paper presents an analysis of the Low-Complexity Acoustic Scene Classification task in DCASE 2022 Challenge. The task was a continuation from the previous years, but the low-c…
Zero-Shot Audio Classification using Image Embeddings
Duygu Dogan, Huang Xie, Toni Heittola +1
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 typica…
Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment
Shanshan Wang, Archontis Politis, Annamaria Mesaros +1
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 vis…
Language-based Audio Retrieval Task in DCASE 2022 Challenge
Huang Xie, Samuel Lipping, Tuomas Virtanen
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 DC…
STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events
Archontis Politis, Kazuki Shimada, Parthasaarathy Sudarsanam +7
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 co…
Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering
Samuel Lipping, Parthasaarathy Sudarsanam, Konstantinos Drossos +1
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 an…
Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers
Sharath Adavanne, Archontis Politis, Tuomas Virtanen
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…