English
Related papers

Related papers: Exploiting Consistency-Preserving Loss and Percept…

200 papers

Pre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks. However, their potential in target speech extraction (TSE) has not been fully exploited. TSE aims to extract the speech of a target…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-21 Junyi Peng , Marc Delcroix , Tsubasa Ochiai , Oldrich Plchot , Shoko Araki , Jan Cernocky

In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Jiale Chen

Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on speech tasks using only small amounts of annotated data. The high number of proposed approaches…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-02 Salah Zaiem , Youcef Kemiche , Titouan Parcollet , Slim Essid , Mirco Ravanelli

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…

Computation and Language · Computer Science 2021-05-04 Jinchuan Tian , Rongzhi Gu , Helin Wang , Yuexian Zou

Self-Supervised Learning (SSL) methods operate on unlabeled data to learn robust representations useful for downstream tasks. Most SSL methods rely on augmentations obtained by transforming the 2D image pixel map. These augmentations ignore…

Computer Vision and Pattern Recognition · Computer Science 2023-01-30 Sumukh Aithal , Anirudh Goyal , Alex Lamb , Yoshua Bengio , Michael Mozer

Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-07 Bryce Irvin , Marko Stamenovic , Mikolaj Kegler , Li-Chia Yang

Self-supervised learning (SSL) has drawn an increased attention in the field of speech processing. Recent studies have demonstrated that contrastive learning is able to learn discriminative speaker embeddings in a self-supervised manner.…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-23 Chunlei Zhang , Dong Yu

We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive…

Computer Vision and Pattern Recognition · Computer Science 2021-08-23 Yuanyi Zhong , Bodi Yuan , Hong Wu , Zhiqiang Yuan , Jian Peng , Yu-Xiong Wang

Self-supervised facial representation has recently attracted increasing attention due to its ability to perform face understanding without relying on large-scale annotated datasets heavily. However, analytically, current contrastive-based…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Yuanyuan Liu , Wenbin Wang , Yibing Zhan , Shaoze Feng , Kejun Liu , Zhe Chen

Semantic Textual Similarity (STS) constitutes a critical research direction in computational linguistics and serves as a key indicator of the encoding capabilities of embedding models. Driven by advances in pre-trained language models and…

Computation and Language · Computer Science 2024-10-08 Bowen Zhang , Chunping Li

Estimating time-frequency domain masks for single-channel speech enhancement using deep learning methods has recently become a popular research field with promising results. In this paper, we propose a novel components loss (CL) for the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-15 Ziyi Xu , Samy Elshamy , Ziyue Zhao , Tim Fingscheidt

Recent work has explored using self-supervised learning (SSL) speech representations such as wav2vec2.0 as the representation medium in standard two-stage TTS, in place of conventionally used mel-spectrograms. It is however unclear which…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-11 Siyang Wang , Gustav Eje Henter , Joakim Gustafson , Éva Székely

Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-02 Salah Zaiem , Titouan Parcollet , Slim Essid

In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as…

Computation and Language · Computer Science 2023-11-28 Shuyue Stella Li , Beining Xu , Xiangyu Zhang , Hexin Liu , Wenhan Chao , Leibny Paola Garcia

Most state-of-the-art self-supervised speaker verification systems rely on a contrastive-based objective function to learn speaker representations from unlabeled speech data. We explore different ways to improve the performance of these…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-25 Theo Lepage , Reda Dehak

Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 Mohammad Alkhalefi , Georgios Leontidis , Mingjun Zhong

Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content information in…

Sound · Computer Science 2025-05-27 Giuseppe Ruggiero , Matteo Testa , Jurgen Van de Walle , Luigi Di Caro

End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervision. This could result in recognition errors due to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-22 Li Fu , Xiaoxiao Li , Runyu Wang , Lu Fan , Zhengchen Zhang , Meng Chen , Youzheng Wu , Xiaodong He

Self-supervised learning (SSL) has recently shown remarkable results in closing the gap between supervised and unsupervised learning. The idea is to learn robust features that are invariant to distortions of the input data. Despite its…

Sound · Computer Science 2023-03-08 Bac Nguyen , Stefan Uhlich , Fabien Cardinaux