X Shi, F Yu, Y Lu, Y Liang, Q Feng… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common …
Africa has a very poor doctor-to-patient ratio. At very busy clinics, doctors could see 30+ patients per day—a heavy patient burden compared with developed countries—but …
Automatic speech recognition (ASR) systems have seen substantial improvements in the past decade; however, not for all speaker groups. Recent research shows that bias exists …
A Hinsvark, N Delworth, M Del Rio… - arXiv preprint arXiv …, 2021 - arxiv.org
Automatic Speech Recognition (ASR) systems generalize poorly on accented speech. The phonetic and linguistic variability of accents present hard challenges for ASR systems today …
Self-supervised learning (SSL) for rich speech representations has achieved empirical success in low-resource Automatic Speech Recognition (ASR) and other speech processing …
Q Li, Q Mai, M Wang, M Ma - Artificial Intelligence Review, 2024 - Springer
As a multi-ethnic country with a large population, China is endowed with diverse dialects, which brings considerable challenges to speech recognition work. In fact, due to …
A Prasad, P Jyothi - Proceedings of the 58th annual meeting of the …, 2020 - aclanthology.org
In this work, we present a detailed analysis of how accent information is reflected in the internal representation of speech in an end-to-end automatic speech recognition (ASR) …
Accents mismatching is a critical problem for end-to-end ASR. This paper aims to address this problem by building an accent-robust RNN-T system with domain adversarial training …
Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two …