English
Related papers

Related papers: Rethinking Discrete Speech Representation Tokens f…

200 papers

Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically,…

Computation and Language · Computer Science 2024-10-29 Opeyemi Osakuade , Simon King

The careful construction of audio representations has become a dominant feature in the design of approaches to many speech tasks. Increasingly, such approaches have emphasized "disentanglement", where a representation contains only parts of…

Speech synthesis might hold the key to low-resource speech recognition. Data augmentation techniques have become an essential part of modern speech recognition training. Yet, they are simple, naive, and rarely reflect real-world conditions.…

Computation and Language · Computer Science 2020-12-25 Deblin Bagchi , Shannon Wotherspoon , Zhuolin Jiang , Prasanna Muthukumar

State-of-the-art Automatic Speech Recognition (ASR) systems are known to exhibit disparate performance on varying speech accents. To improve performance on a specific target accent, a commonly adopted solution is to finetune the ASR model…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-18 Suraj Kothawade , Anmol Mekala , Chandra Sekhara D , Mayank Kothyari , Rishabh Iyer , Ganesh Ramakrishnan , Preethi Jyothi

Objective: Speech tests aim to estimate discrimination loss or speech recognition threshold (SRT). This paper investigates the potential to estimate SRTs from clinical data that target at characterizing the discrimination loss. Knowledge…

Sound · Computer Science 2025-01-16 Mareike Buhl , Eugen Kludt , Lena Schell-Majoor , Paul Avan , Marta Campi

Discrete speech tokens have gained attention for their storage efficiency and integration with Large Language Models (LLMs). They are commonly categorized into acoustic and semantic tokens, with the latter being more advantageous for…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-04 Mohan Shi , Natarajan Balaji Shankar , Kaiyuan Zhang , Zilai Wang , Abeer Alwan

Accents play a pivotal role in shaping human communication, enhancing our ability to convey and comprehend messages with clarity and cultural nuance. While there has been significant progress in Automatic Speech Recognition (ASR),…

Computation and Language · Computer Science 2025-06-24 Bonaventure F. P. Dossou

Aiming at reducing the reliance on expensive human annotations, data synthesis for Automatic Speech Recognition (ASR) has remained an active area of research. While prior work mainly focuses on synthetic speech generation for ASR data…

With recent rapid growth of large language models (LLMs), discrete speech tokenization has played an important role for injecting speech into LLMs. However, this discretization gives rise to a loss of information, consequently impairing…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-23 Zhichao Huang , Chutong Meng , Tom Ko

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

Computation and Language · Computer Science 2026-02-17 Ligong Lei , Wenwen Lu , Xudong Pang , Zaokere Kadeer , Aishan Wumaier

This paper introduces a discrete diffusion model (DDM) framework for text-aligned speech tokenization and reconstruction. By replacing the auto-regressive speech decoder with a discrete diffusion counterpart, our model achieves…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-25 Pin-Jui Ku , He Huang , Jean-Marie Lemercier , Subham Sekhar Sahoo , Zhehuai Chen , Ante Jukić

Accent recognition with deep learning framework is a similar work to deep speaker identification, they're both expected to give the input speech an identifiable representation. Compared with the individual-level features learned by speaker…

Sound · Computer Science 2021-08-26 Wei Wang , Chao Zhang , Xiaopei Wu

Nowadays, the main problem of deep learning techniques used in the development of automatic speech recognition (ASR) models is the lack of transcribed data. The goal of this research is to propose a new data augmentation method to improve…

Computation and Language · Computer Science 2022-04-04 Rodolfo Zevallos

Language identification from speech is a common preprocessing step in many spoken language processing systems. In recent years, this field has seen fast progress, mostly due to the use of self-supervised models pretrained on multilingual…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-04 Kunnar Kukk , Tanel Alumäe

While automatic speech recognition (ASR) systems have achieved remarkable performance with large-scale datasets, their efficacy remains inadequate in low-resource settings, encompassing dialects, accents, minority languages, and long-tail…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-23 Guanrou Yang , Fan Yu , Ziyang Ma , Zhihao Du , Zhifu Gao , Shiliang Zhang , Xie Chen

The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…

Computation and Language · Computer Science 2015-10-20 Yajie Miao , Mohammad Gowayyed , Florian Metze

In accented voice conversion or accent conversion, we seek to convert the accent in speech from one another while preserving speaker identity and semantic content. In this study, we formulate a novel method for creating multi-accented…

Sound · Computer Science 2025-01-13 Sho Inoue , Shuai Wang , Wanxing Wang , Pengcheng Zhu , Mengxiao Bi , Haizhou Li

Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such representations may be skewed toward canonical data…

Computation and Language · Computer Science 2023-07-04 Anshu Bhatia , Sanchit Sinha , Saket Dingliwal , Karthik Gopalakrishnan , Sravan Bodapati , Katrin Kirchhoff

Automatic Speech Recognition (ASR) based on Recurrent Neural Network Transducers (RNN-T) is gaining interest in the speech community. We investigate data selection and preparation choices aiming for improved robustness of RNN-T ASR to…

Computation and Language · Computer Science 2020-12-14 Valentin Mendelev , Tina Raissi , Guglielmo Camporese , Manuel Giollo

Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS)…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Xuehao Zhou , Mingyang Zhang , Yi Zhou , Zhizheng Wu , Haizhou Li