English
Related papers

Related papers: Gender domain adaptation for automatic speech reco…

200 papers

Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. In this work, we treat the gender as domains (e.g., male vs. female) and present a standard domain adaptation…

Computation and Language · Computer Science 2022-04-13 Xiaolei Huang

Automatic speech recognition models are often adapted to improve their accuracy in a new domain. A potential drawback of model adaptation to new domains is catastrophic forgetting, where the Word Error Rate on the original domain is…

Sound · Computer Science 2022-10-10 Somshubra Majumdar , Shantanu Acharya , Vitaly Lavrukhin , Boris Ginsburg

In this paper, we demonstrate the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks. We start with a pre-trained English ASR model and show that transfer learning can be effectively…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-12 Jocelyn Huang , Oleksii Kuchaiev , Patrick O'Neill , Vitaly Lavrukhin , Jason Li , Adriana Flores , Georg Kucsko , Boris Ginsburg

Deep speaker embedding has achieved satisfactory performance in speaker verification. By enforcing the neural model to discriminate the speakers in the training set, deep speaker embedding (called `x-vectors`) can be derived from the hidden…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-28 Xueyi Wang , Lantian Li , Dong Wang

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

Machine Learning · Computer Science 2023-03-15 Lucas Maison , Yannick Estève

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced.…

Sound · Computer Science 2024-06-28 Yehoshua Dissen , Shiry Yonash , Israel Cohen , Joseph Keshet

The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-of-the-art ASR. Despite LLMs being trained with an extensive…

Computation and Language · Computer Science 2024-12-11 Yingyi Ma , Zhe Liu , Ozlem Kalinli

General-purpose ASR underperforms for atypical speakers, such as L2 learners, reinforcing bias and limiting use in education and accessibility. Using the CEFR-graded Speak and Improve corpus, we show that naive fine-tuning of Whisper…

Sound · Computer Science 2025-10-14 Ling Sun , Charlotte Zhu , Shuju Shi

Pre-trained Transformer-based speech models have shown striking performance when fine-tuned on various downstream tasks such as automatic speech recognition and spoken language identification (SLID). However, the problem of domain mismatch…

Computation and Language · Computer Science 2023-12-13 Mohammed Maqsood Shaik , Dietrich Klakow , Badr M. Abdullah

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on…

Computation and Language · Computer Science 2024-01-12 Jiaxin Guo , Minghan Wang , Xiaosong Qiao , Daimeng Wei , Hengchao Shang , Zongyao Li , Zhengzhe Yu , Yinglu Li , Chang Su , Min Zhang , Shimin Tao , Hao Yang

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-16 Keqi Deng , Songjun Cao , Long Ma

This article presents a novel approach for learning domain-invariant speaker embeddings using Generative Adversarial Networks. The main idea is to confuse a domain discriminator so that is can't tell if embeddings are from the source or…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-08 Gautam Bhattacharya , Joao Monteiro , Jahangir Alam , Patrick Kenny

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…

Sound · Computer Science 2022-06-22 Junyi Ao , Ziqiang Zhang , Long Zhou , Shujie Liu , Haizhou Li , Tom Ko , Lirong Dai , Jinyu Li , Yao Qian , Furu Wei

We report on the curation of several publicly available datasets for age and gender prediction. Furthermore, we present experiments to predict age and gender with models based on a pre-trained wav2vec 2.0. Depending on the dataset, we…

Sound · Computer Science 2023-06-30 Felix Burkhardt , Johannes Wagner , Hagen Wierstorf , Florian Eyben , Björn Schuller

Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benefiting from the diverse data sources such as different…

Computation and Language · Computer Science 2023-02-06 Bo Li , Dongseong Hwang , Zhouyuan Huo , Junwen Bai , Guru Prakash , Tara N. Sainath , Khe Chai Sim , Yu Zhang , Wei Han , Trevor Strohman , Francoise Beaufays

Despite the growing advancements in Automatic Speech Recognition (ASR) models, the development of robust models for underrepresented languages, such as Nepali, remains a challenge. This research focuses on making an exhaustive and…

Computation and Language · Computer Science 2024-11-20 Sanjay Rijal , Shital Adhikari , Manish Dahal , Manish Awale , Vaghawan Ojha

Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-22 Jenthe Thienpondt , Kris Demuynck

When translating words referring to the speaker, speech translation (ST) systems should not resort to default masculine generics nor rely on potentially misleading vocal traits. Rather, they should assign gender according to the speakers'…

Computation and Language · Computer Science 2023-10-25 Dennis Fucci , Marco Gaido , Sara Papi , Mauro Cettolo , Matteo Negri , Luisa Bentivogli

Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical workaround, it often introduces systematic, accent-specific…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-21 Yi-Cheng Lin , Yu-Hsuan Li Liang , Hsuan Su , Tzu-Quan Lin , Shang-Tse Chen , Yun-Nung Chen , Hung-yi Lee