English
Related papers

Related papers: Chunk Based Speech Pre-training with High Resoluti…

200 papers

Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-06 Jakob Poncelet , Yujun Wang , Hugo Van hamme

Self-supervised learning (SSL) representations from massively multilingual models offer a promising solution for low-resource language speech tasks. Despite advancements, language adaptation in TTS systems remains an open problem. This…

Self-supervised learning (SSL) has advanced speech processing but suffers from quadratic complexity due to self-attention. To address this, SummaryMixing (SM) has been proposed as a linear-time alternative that summarizes entire utterances…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-11 Aditya Srinivas Menon , Kumud Tripathi , Raj Gohil , Pankaj Wasnik

We propose the Chunkwise Aligner, a novel architecture for streaming automatic speech recognition (ASR). While the Transducer is the standard model for streaming ASR, its training is costly due to the need to compute all possible…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-13 Wen Shen Teo , Takafumi Moriya , Masato Mimura

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

Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio…

Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio…

Sound · Computer Science 2023-07-25 Peranut Nimitsurachat , Peter Washington

People exploit the predictability of lexical structures during text comprehension. Though predictable structure is also present in speech, the degree to which prosody, e.g. intonation, tempo, and loudness, contributes to such structure…

Computation and Language · Computer Science 2025-06-04 Sarenne Wallbridge , Christoph Minixhofer , Catherine Lai , Peter Bell

Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Zaid Khan , Vijay Kumar BG , Xiang Yu , Samuel Schulter , Manmohan Chandraker , Yun Fu

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a…

Computation and Language · Computer Science 2021-10-22 Ankur Bapna , Yu-an Chung , Nan Wu , Anmol Gulati , Ye Jia , Jonathan H. Clark , Melvin Johnson , Jason Riesa , Alexis Conneau , Yu Zhang

Deep neural networks have been widely used in communication signal recognition and achieved remarkable performance, but this superiority typically depends on using massive examples for supervised learning, whereas training a deep neural…

Signal Processing · Electrical Eng. & Systems 2023-11-15 Weidong Wang , Hongshu Liao , Lu Gan

Self-supervised learning (SSL) achieves great success in monaural speech enhancement, while the accuracy of the target speech estimation, particularly for unseen speakers, remains inadequate with existing pre-tasks. As speech signal…

Sound · Computer Science 2022-06-13 Yi Li , ShuangLin Li , Yang Sun , Syed Mohsen Naqvi

Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the history speech context and past translations so that quality and latency, including computation overhead,…

Computation and Language · Computer Science 2025-06-17 Siqi Ouyang , Xi Xu , Lei Li

Sign language pre-training has gained increasing attention for its ability to enhance performance across various sign language understanding (SLU) tasks. However, existing methods often suffer from a gap between pre-training and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Zecheng Li , Wengang Zhou , Weichao Zhao , Kepeng Wu , Hezhen Hu , Houqiang Li

Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar…

In this paper, we tackle the problem of online semi-supervised learning (SSL). When data arrive in a stream, the dual problems of computation and data storage arise for any SSL method. We propose a fast approximate online SSL algorithm that…

Machine Learning · Computer Science 2012-03-19 Michal Valko , Branislav Kveton , Ling Huang , Daniel Ting

Conventional text-to-SQL studies are limited to a single task with a fixed-size training and test set. When confronted with a stream of tasks common in real-world applications, existing methods struggle with the problems of insufficient…

Computation and Language · Computer Science 2022-11-22 Yongrui Chen , Xinnan Guo , Tongtong Wu , Guilin Qi , Yang Li , Yang Dong

Multilingual self-supervised learning (SSL) has often lagged behind state-of-the-art (SOTA) methods due to the expenses and complexity required to handle many languages. This further harms the reproducibility of SSL, which is already…

Computation and Language · Computer Science 2023-09-29 William Chen , Jiatong Shi , Brian Yan , Dan Berrebbi , Wangyou Zhang , Yifan Peng , Xuankai Chang , Soumi Maiti , Shinji Watanabe

Self-supervised learning (SSL), which aims to learn meaningful prior representations from unlabeled data, has been proven effective for skeleton-based action understanding. Different from the image domain, skeleton data possesses sparser…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Jiahang Zhang , Lilang Lin , Shuai Yang , Jiaying Liu

Self-supervised learning (SSL) has achieved great success in various areas including speech processing. Recently, it is proven that speech based SSL models are able to extract superior universal representations on a range of downstream…

Sound · Computer Science 2022-12-21 Changli Tang , Yujin Wang , Xie Chen , Wei-Qiang Zhang