paper-with-me

Papers

Accented Speech Recognition: A Survey

2021-04-21 · Arthur Hinsvark, Natalie Delworth, Miguel Del Rio, Quinten McNamara, Joshua Dong, Ryan Westerman, Michelle Huang, Joseph Palakapilly, Jennifer Drexler, Ilya Pirkin, Nishchal Bhandari, Miguel Jette

Automatic Speech Recognition (ASR) systems generalize poorly on accented speech. The phonetic and linguistic variability of accents present hard challenges for ASR systems today in both data collection and modeling strategies. The resulting bias in ASR performance across accents comes at a cost to both users and providers of ASR. We present a survey of current promising approaches to accented speech recognition and highlight the key challenges in the space. Approaches mostly focus on single model generalization and accent feature engineering. Among the challenges, lack of a standard benchmark makes research and comparison especially difficult.

📄 PDF Abstract BibTeX arXiv:2104.10747

Code (0)

등록된 구현이 없습니다.

Tasks

Accented Speech RecognitionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Feature Engineeringspeech-recognitionSpeech RecognitionSurvey

Similar Papers 제목 키워드 기반

Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis

2024-07-04 · Cong-Thanh Do, Shuhei Imai, Rama Doddipatla, Thomas Hain

This paper investigates the use of unsupervised text-to-speech synthesis (TTS) as a data augmentation method to improve accented speech recognition. TTS systems are trained with a small amount of accented speech training…

Accented Speech RecognitionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentation+7

Accented Speech Recognition: Benchmarking, Pre-training, and Diverse Data

2022-05-16 · Alëna Aksënova, Zhehuai Chen, Chung-Cheng Chiu, Daan van Esch 외

Building inclusive speech recognition systems is a crucial step towards developing technologies that speakers of all language varieties can use. Therefore, ASR systems must work for everybody independently of the way the…

Accented Speech RecognitionBenchmarkingDiversityspeech-recognition+1

Clustering and Mining Accented Speech for Inclusive and Fair Speech Recognition

2024-08-05

Modern automatic speech recognition (ASR) systems are typically trained on more than tens of thousands hours of speech data, which is one of the main factors for their great success. However, the distribution of such dat…

Domain Adversarial Training for Accented Speech Recognition

2018-06-07 · Sining Sun, Ching-Feng Yeh, Mei-Yuh Hwang, Mari Ostendorf 외

In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data ("standard" accent) and unl…

Accented Speech RecognitionMulti-Task Learningspeech-recognitionSpeech Recognition

Accented Speech Recognition Inspired by Human Perception

2021-04-09 · Xiangyun Chu, Elizabeth Combs, Amber Wang, Michael Picheny

While improvements have been made in automatic speech recognition performance over the last several years, machines continue to have significantly lower performance on accented speech than humans. In addition, the most s…

Accented Speech RecognitionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognition+1