English
Related papers

Related papers: Where Do Self-Supervised Speech Models Become Unfa…

200 papers

Speech enhancement has seen great improvement in recent years using end-to-end neural networks. However, most models are agnostic to the spoken phonetic content. Recently, several studies suggested phonetic-aware speech enhancement, mostly…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-23 Or Tal , Moshe Mandel , Felix Kreuk , Yossi Adi

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…

Sound · Computer Science 2026-01-28 Tianhua Li , Chenda Li , Wei Wang , Xin Zhou , Xihui Chen , Jianqing Gao , Yanmin Qian

The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an…

Computation and Language · Computer Science 2023-03-03 Philipp Klumpp , Pooja Chitkara , Leda Sarı , Prashant Serai , Jilong Wu , Irina-Elena Veliche , Rongqing Huang , Qing He

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

Computation and Language · Computer Science 2019-02-21 Ozan Caglayan , Ramon Sanabria , Shruti Palaskar , Loïc Barrault , Florian Metze

Pre-trained automatic speech recognition (ASR) models have demonstrated strong performance on a variety of tasks. However, their performance can degrade substantially when the input audio comes from different recording channels. While…

Sound · Computer Science 2025-08-25 Kuan-Tang Huang , Li-Wei Chen , Hung-Shin Lee , Berlin Chen , Hsin-Min Wang

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-27 Jianwei Tai , Xiaoqi Jia , Qingjia Huang , Weijuan Zhang , Haichao Du , Shengzhi Zhang

Automatic Speech Recognition (ASR) systems can be trained to achieve remarkable performance given large amounts of manually transcribed speech, but large labeled data sets can be difficult or expensive to acquire for all languages of…

Computation and Language · Computer Science 2022-03-22 Hanan Aldarmaki , Asad Ullah , Nazar Zaki

Speech foundation models (SFMs) have demonstrated strong performance across a variety of downstream tasks, including speech intelligibility prediction for hearing-impaired people (SIP-HI). However, optimizing SFMs for SIP-HI has been…

Artificial Intelligence · Computer Science 2025-05-14 Haoshuai Zhou , Boxuan Cao , Changgeng Mo , Linkai Li , Shan Xiang Wang

In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to…

Computation and Language · Computer Science 2023-12-18 Tzu-Ting Yang , Hsin-Wei Wang , Berlin Chen

End-to-end automatic speech recognition (ASR) models aim to learn a generalised speech representation. However, there are limited tools available to understand the internal functions and the effect of hierarchical dependencies within the…

Computation and Language · Computer Science 2022-05-20 Anna Ollerenshaw , Md Asif Jalal , Thomas Hain

Self-supervised learning (SSL) for rich speech representations has achieved empirical success in low-resource Automatic Speech Recognition (ASR) and other speech processing tasks, which can mitigate the necessity of a large amount of…

Machine Learning · Computer Science 2025-01-07 Yonggan Fu , Yang Zhang , Kaizhi Qian , Zhifan Ye , Zhongzhi Yu , Cheng-I Lai , Yingyan Celine Lin

Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Alexandros Haliassos , Rodrigo Mira , Honglie Chen , Zoe Landgraf , Stavros Petridis , Maja Pantic

Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-22 Yi-Cheng Lin , Tzu-Quan Lin , Chih-Kai Yang , Ke-Han Lu , Wei-Chih Chen , Chun-Yi Kuan , Hung-yi Lee

Speaker recognition is increasingly used in several everyday applications including smart speakers, customer care centers and other speech-driven analytics. It is crucial to accurately evaluate and mitigate biases present in machine…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-18 Raghuveer Peri , Krishna Somandepalli , Shrikanth Narayanan

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

Recently proposed speech recognition systems are designed to predict using representations generated by their top layers, employing greedy decoding which isolates each timestep from the rest of the sequence. Aiming for improved performance,…

Computation and Language · Computer Science 2022-04-06 Tomer Wullach , Shlomo E. Chazan

Speech foundation models (SFMs) are increasingly hailed as powerful computational models of human speech perception. However, since their representations are inherently black-box, it remains unclear what drives their alignment with brain…

Neurons and Cognition · Quantitative Biology 2025-09-26 Riki Shimizu , Richard J. Antonello , Chandan Singh , Nima Mesgarani

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

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Machine Learning · Computer Science 2026-05-12 Collin Francel

Speech-aware LLMs (SLLMs) have recently achieved state-of-the-art ASR performance; however, they still fail to accurately transcribe bias words that appear rarely or never in the training data. Contextual biasing mechanisms are commonly…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-15 Sashi Novitasari , Takashi Fukuda , Kurata Gakuto , George Saon