English
Related papers

Related papers: Can you Remove the Downstream Model for Speaker Re…

200 papers

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

Sound · Computer Science 2022-10-07 Yehoshua Dissen , Felix Kreuk , Joseph Keshet

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

Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning. The former severely limits the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-02 Salah Zaiem , Titouan Parcollet , Slim Essid

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

Sound · Computer Science 2025-10-07 Takashi Maekaku , Keita Goto , Jinchuan Tian , Yusuke Shinohara , Shinji Watanabe

Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and…

Computation and Language · Computer Science 2023-12-19 Luis Lugo , Valentin Vielzeuf

In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e.g., 0.3 seconds) by a carefully designed convolutional & time-delay deep neural network (CT-DNN) model. By enforcing the model to…

Sound · Computer Science 2018-02-28 Lantian Li , Zhiyuan Tang , Dong Wang , Thomas Fang Zheng

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Sound · Computer Science 2024-08-27 Zhaoxi Mu , Xinyu Yang , Sining Sun , Qing Yang

Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speech SSL models, such as WavLM, employ masked prediction training to encode general-purpose representations. In contrast,…

Computation and Language · Computer Science 2024-02-01 Takanori Ashihara , Marc Delcroix , Takafumi Moriya , Kohei Matsuura , Taichi Asami , Yusuke Ijima

In this work we introduce a semi-supervised approach to the voice conversion problem, in which speech from a source speaker is converted into speech of a target speaker. The proposed method makes use of both parallel and non-parallel…

Machine Learning · Statistics 2019-10-02 Cory Stephenson , Gokce Keskin , Anil Thomas , Oguz H. Elibol

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-20 Xiaojiao Chen , Sheng Li , Jiyi Li , Hao Huang , Yang Cao , Liang He

For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-04 Po-Han Chi , Pei-Hung Chung , Tsung-Han Wu , Chun-Cheng Hsieh , Yen-Hao Chen , Shang-Wen Li , Hung-yi Lee

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…

Sound · Computer Science 2022-01-25 Zhengyang Chen , Sanyuan Chen , Yu Wu , Yao Qian , Chengyi Wang , Shujie Liu , Yanmin Qian , Michael Zeng

Several methods have recently been proposed to analyze speech and automatically infer the personality of the speaker. These methods often rely on prosodic and other hand crafted speech processing features extracted with off-the-shelf…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Marc-André Carbonneau , Eric Granger , Yazid Attabi , Ghyslain Gagnon

Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…

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

Network pruning is of great importance due to the elimination of the unimportant weights or features activated due to the network over-parametrization. Advantages of sparsity enforcement include preventing the overfitting and speedup.…

Sound · Computer Science 2018-08-13 Sara Sedighi , Shayan Ramhormozi

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in…

Computation and Language · Computer Science 2021-10-13 Sanyuan Chen , Yu Wu , Chengyi Wang , Zhengyang Chen , Zhuo Chen , Shujie Liu , Jian Wu , Yao Qian , Furu Wei , Jinyu Li , Xiangzhan Yu

Self-supervised learning (SSL) based models have been shown to generate powerful representations that can be used to improve the performance of downstream speech tasks. Several state-of-the-art SSL models are available, and each of these…

Computation and Language · Computer Science 2023-02-21 A Arunkumar , Vrunda N Sukhadia , S. Umesh

Speech recognition system performance degrades in noisy environments. If the acoustic models are built using features of clean utterances, the features of a noisy test utterance would be acoustically mismatched with the trained model. This…

Computation and Language · Computer Science 2015-07-16 D. S. Pavan Kumar

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training…

Computation and Language · Computer Science 2023-01-04 Sreepratha Ram , Hanan Aldarmaki

It was shown in literature that speech representations extracted by self-supervised pre-trained models exhibit similarities with brain activations of human for speech perception and fine-tuning speech representation models on downstream…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-14 Hengyu Li , Kangdi Mei , Zhaoci Liu , Yang Ai , Liping Chen , Jie Zhang , Zhenhua Ling