English
Related papers

Related papers: A Domain Adaptation Framework for Speech Recogniti…

200 papers

ASR model deployment environment is ever-changing, and the incoming speech can be switched across different domains during a session. This brings a challenge for effective domain adaptation when only target domain text data is available,…

Computation and Language · Computer Science 2023-03-03 Rao Ma , Xiaobo Wu , Jin Qiu , Yanan Qin , Haihua Xu , Peihao Wu , Zejun Ma

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents.…

Computation and Language · Computer Science 2024-05-24 Yuchen Hu , Chen Chen , Chao-Han Huck Yang , Chengwei Qin , Pin-Yu Chen , Eng Siong Chng , Chao Zhang

Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for…

Computation and Language · Computer Science 2021-06-16 Chak-Fai Li , Francis Keith , William Hartmann , Matthew Snover , Owen Kimball

In this work, we present our submission to the Speech Accessibility Project challenge for dysarthric speech recognition. We integrate parameter-efficient fine-tuning with latent audio representations to improve an encoder-decoder ASR…

Adaption of end-to-end speech recognition systems to new tasks is known to be challenging. A number of solutions have been proposed which apply external language models with various fusion methods, possibly with a combination of two-pass…

Computation and Language · Computer Science 2021-06-10 Janne Pylkkönen , Antti Ukkonen , Juho Kilpikoski , Samu Tamminen , Hannes Heikinheimo

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-21 Manuel Giollo , Deniz Gunceler , Yulan Liu , Daniel Willett

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-19 Yingzhu Zhao , Chongjia Ni , Cheung-Chi Leung , Shafiq Joty , Eng Siong Chng , Bin Ma

Large speech foundation models achieve strong performance across many domains, but they often require adaptation to handle local needs such as code-switching, where speakers mix languages within the same utterance. Direct fine-tuning of…

Computation and Language · Computer Science 2025-10-22 Enes Yavuz Ugan , Ngoc-Quan Pham , Alexander Waibel

Data efficient voice cloning aims at synthesizing target speaker's voice with only a few enrollment samples at hand. To this end, speaker adaptation and speaker encoding are two typical methods based on base model trained from multiple…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Jian Cong , Shan Yang , Lei Xie , Guoqiao Yu , Guanglu Wan

This paper introduces three self-contained data augmentation methods for low-resource Automatic Speech Recognition (ASR). Our techniques first generate novel text--using gloss-based replacement, random replacement, or an LLM-based…

Computation and Language · Computer Science 2026-01-21 Katsumi Ibaraki , David Chiang

Automatic recognition of disordered and elderly speech remains a highly challenging task to date due to the difficulty in collecting such data in large quantities. This paper explores a series of approaches to integrate domain adapted SSL…

Sound · Computer Science 2023-06-23 Shujie Hu , Xurong Xie , Zengrui Jin , Mengzhe Geng , Yi Wang , Mingyu Cui , Jiajun Deng , Xunying Liu , Helen Meng

In this work, we investigate the Meta PL unsupervised domain adaptation framework for Automatic Speech Recognition (ASR). We introduce a Multi-Stage Domain Adaptation pipeline (MSDA), a sample-efficient, two-stage adaptation approach that…

Computation and Language · Computer Science 2025-06-03 Dimitrios Damianos , Georgios Paraskevopoulos , Alexandros Potamianos

Recommender systems have become a cornerstone of personalized user experiences, yet their development typically involves significant manual intervention, including dataset-specific feature engineering, hyperparameter tuning, and…

Information Retrieval · Computer Science 2025-04-24 Tri Kurniawan Wijaya , Edoardo D'Amico , Xinyang Shao

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

Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address…

Computation and Language · Computer Science 2024-10-18 Abhishek Gupta , Amruta Parulekar , Sameep Chattopadhyay , Preethi Jyothi

Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Da Li , Timothy Hospedales

As human-machine voice interfaces provide easy access to increasingly intelligent machines, many state-of-the-art automatic speech recognition (ASR) systems are proposed. However, commercial ASR systems usually have poor performance on…

Computation and Language · Computer Science 2023-09-28 Yanan Jia

Unsupervised domain adaptation leverages abundant labeled data from various source domains to generalize onto unlabeled target data. Prior research has primarily focused on learning domain-invariant features across the source and target…

Computation and Language · Computer Science 2025-03-10 Jie He , Wendi Zhou , Xiang Lorraine Li , Jeff Z. Pan

Large language models (LLMs) have been successfully applied for rescoring automatic speech recognition (ASR) hypotheses. However, their ability to rescore ASR hypotheses of casual conversations has not been sufficiently explored. In this…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-28 Atsunori Ogawa , Naoyuki Kamo , Kohei Matsuura , Takanori Ashihara , Takafumi Moriya , Takatomo Kano , Naohiro Tawara , Marc Delcroix

Developing a practical speech recognizer for a low resource language is challenging, not only because of the (potentially unknown) properties of the language, but also because test data may not be from the same domain as the available…

Computation and Language · Computer Science 2018-10-02 Siddharth Dalmia , Xinjian Li , Florian Metze , Alan W. Black
‹ Prev 1 3 4 5 6 7 10 Next ›