English
Related papers

Related papers: Improving Speech Inversion Through Self-Supervised…

200 papers

Recent years have witnessed great strides in self-supervised learning (SSL) on the speech processing. The SSL model is normally pre-trained on a great variety of unlabelled data and a large model size is preferred to increase the modeling…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-08 Yujin Wang , Changli Tang , Ziyang Ma , Zhisheng Zheng , Xie Chen , Wei-Qiang Zhang

Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-28 Wenda Chen , Jonathan Huang , Tobias Bocklet

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

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

Sound · Computer Science 2025-07-18 Luca Della Libera , Cem Subakan , Mirco Ravanelli

To understand why self-supervised learning (SSL) models have empirically achieved strong performances on several speech-processing downstream tasks, numerous studies have focused on analyzing the encoded information of the SSL layer…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-07 Jialu Li , Mark Hasegawa-Johnson , Nancy L. McElwain

At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…

Machine Learning · Computer Science 2024-05-29 Sharut Gupta , Chenyu Wang , Yifei Wang , Tommi Jaakkola , Stefanie Jegelka

In recent Text-to-Speech (TTS) systems, a neural vocoder often generates speech samples by solely conditioning on acoustic features predicted from an acoustic model. However, there are always distortions existing in the predicted acoustic…

Sound · Computer Science 2023-04-25 Jianzong Wang , Xulong Zhang , Haobin Tang , Aolan Sun , Ning Cheng , Jing Xiao

Speech Emotion Recognition (SER) often operates on speech segments detected by a Voice Activity Detection (VAD) model. However, VAD models may output flawed speech segments, especially in noisy environments, resulting in degraded…

Sound · Computer Science 2024-10-18 Natsuo Yamashita , Masaaki Yamamoto , Yohei Kawaguchi

We can estimate the size of the speakers based on their speech sounds alone. We had proposed an auditory computational theory of the Stabilised Wavelet-Mellin Transform (SWMT), which segregates information about the size and shape of the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Toshio Irino , Shintaro Doan

In this work, we observe a counterintuitive phenomenon in self-supervised learning (SSL): longer training may impair the performance of dense prediction tasks (e.g., semantic segmentation). We refer to this phenomenon as Self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Siran Dai , Qianqian Xu , Peisong Wen , Yang Liu , Qingming Huang

In this paper, we propose to extend the deep, complex U-Network architecture for speech enhancement by incorporating a probabilistic (i.e., variational) latent space model. The proposed model is evaluated against several ablated versions of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-06 Eike J. Nustede , Jörn Anemüller

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with linguistic information. Both of them are beneficial for…

Sound · Computer Science 2022-11-28 Zhuoyuan Yao , Shuo Ren , Sanyuan Chen , Ziyang Ma , Pengcheng Guo , Lei Xie

Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-08 Subrina Sultana , Donald S. Williamson

Self-supervised learning representation (SSLR) has demonstrated its significant effectiveness in automatic speech recognition (ASR), mainly with clean speech. Recent work pointed out the strength of integrating SSLR with single-channel…

Sound · Computer Science 2022-10-20 Yoshiki Masuyama , Xuankai Chang , Samuele Cornell , Shinji Watanabe , Nobutaka Ono

Singing voice beat tracking is a challenging task, due to the lack of musical accompaniment that often contains robust rhythmic and harmonic patterns, something most existing beat tracking systems utilize and can be essential for estimating…

Sound · Computer Science 2025-03-14 Jiajun Deng , Yaolong Ju , Jing Yang , Simon Lui , Xunying Liu

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-02 Qingming Tang

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

Computation and Language · Computer Science 2020-03-25 Alex Bie , Bharat Venkitesh , Joao Monteiro , Md. Akmal Haidar , Mehdi Rezagholizadeh

In large part due to their implicit semantic modeling, self-supervised learning (SSL) methods have significantly increased the performance of valence recognition in speech emotion recognition (SER) systems. Yet, their large size may often…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-20 Danilo de Oliveira , Navin Raj Prabhu , Timo Gerkmann

In this paper, we provide a new perspective on self-supervised speech models from how the training targets are obtained. We generalize the targets extractor into Offline Targets Extractor (Off-TE) and Online Targets Extractor (On-TE). Based…

Computation and Language · Computer Science 2023-06-01 Ziyang Ma , Zhisheng Zheng , Changli Tang , Yujin Wang , Xie Chen