English
Related papers

Related papers: Massively Multilingual ASR on 70 Languages: Tokeni…

200 papers

With the advancement of Self-supervised Learning (SSL) in speech-related tasks, there has been growing interest in utilizing discrete tokens generated by SSL for automatic speech recognition (ASR), as they offer faster processing…

Computation and Language · Computer Science 2024-09-16 Mingyu Cui , Daxin Tan , Yifan Yang , Dingdong Wang , Huimeng Wang , Xiao Chen , Xie Chen , Xunying Liu

We propose a first step toward multilingual end-to-end automatic speech recognition (ASR) by integrating knowledge about speech articulators. The key idea is to leverage a rich set of fundamental units that can be defined "universally"…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Hao Yen , Sabato Marco Siniscalchi , Chin-Hui Lee

In previous works, only parameter weights of ASR models are optimized under fixed-topology architecture. However, the design of successful model architecture has always relied on human experience and intuition. Besides, many hyperparameters…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Yi-Chen Chen , Jui-Yang Hsu , Cheng-Kuang Lee , Hung-yi Lee

Multilingual Automatic Speech Recognition (ASR) models have extended the usability of speech technologies to a wide variety of languages. With how many languages these models have to handle, however, a key to understanding their imbalanced…

Computation and Language · Computer Science 2023-02-28 William Chen , Brian Yan , Jiatong Shi , Yifan Peng , Soumi Maiti , Shinji Watanabe

In this paper, we present a neural spoken language diarization model that supports an unconstrained span of languages within a single framework. Our approach integrates a learnable query-based architecture grounded in multilingual…

Computation and Language · Computer Science 2025-10-02 Sangmin Lee , Woongjib Choi , Jihyun Kim , Hong-Goo Kang

In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck. We propose a non-autoregressive LM-fused ASR system that effectively leverages the parallelization capabilities…

Computation and Language · Computer Science 2024-01-24 W. Ronny Huang , Cyril Allauzen , Tongzhou Chen , Kilol Gupta , Ke Hu , James Qin , Yu Zhang , Yongqiang Wang , Shuo-Yiin Chang , Tara N. Sainath

Building Automatic Speech Recognition (ASR) systems for code-switched speech has recently gained renewed attention due to the widespread use of speech technologies in multilingual communities worldwide. End-to-end ASR systems are a natural…

Computation and Language · Computer Science 2020-10-13 Yash Sharma , Basil Abraham , Karan Taneja , Preethi Jyothi

Multilingual end-to-end models have shown great improvement over monolingual systems. With the development of pre-training methods on speech, self-supervised multilingual speech representation learning like XLSR has shown success in…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-08 Fenglin Ding , Genshun Wan , Pengcheng Li , Jia Pan , Cong Liu

Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, language, while maintaining performance on the original language…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Mengjie Qian , Siyuan Tang , Rao Ma , Kate M. Knill , Mark J. F. Gales

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are considered. The first constructs four separate bilingual…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-09 Astik Biswas , Emre Yılmaz , Febe de Wet , Ewald van der Westhuizen , Thomas Niesler

End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…

Computation and Language · Computer Science 2020-02-17 Marco Dinarelli , Nikita Kapoor , Bassam Jabaian , Laurent Besacier

While large language models (LLM) have made impressive progress in natural language processing, it remains unclear how to utilize them in improving automatic speech recognition (ASR). In this work, we propose to train a single multilingual…

Computation and Language · Computer Science 2023-02-20 Ke Hu , Tara N. Sainath , Bo Li , Nan Du , Yanping Huang , Andrew M. Dai , Yu Zhang , Rodrigo Cabrera , Zhifeng Chen , Trevor Strohman

Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-11 Ilya Sklyar , Anna Piunova , Xianrui Zheng , Yulan Liu

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-12 Changhan Wang , Juan Pino , Jiatao Gu

This paper presents recent progress in the acoustic modelling of under-resourced code-switched (CS) speech in multiple South African languages. We consider two approaches. The first constructs separate bilingual acoustic models…

Computation and Language · Computer Science 2019-10-16 Astik Biswas , Emre Yılmaz , Febe de Wet , Ewald van der Westhuizen , Thomas Niesler

This paper describes the systems developed by SPRING Lab, Indian Institute of Technology Madras, for the ASRU MADASR 2.0 challenge. The systems developed focuses on adapting ASR systems to improve in predicting the language and dialect of…

Computation and Language · Computer Science 2025-11-20 Arjun Gangwar , Kaousheik Jayakumar , S. Umesh

Towards developing high-performing ASR for low-resource languages, approaches to address the lack of resources are to make use of data from multiple languages, and to augment the training data by creating acoustic variations. In this work…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-10 Chunxi Liu , Qiaochu Zhang , Xiaohui Zhang , Kritika Singh , Yatharth Saraf , Geoffrey Zweig

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Computation and Language · Computer Science 2020-02-24 Herman Kamper , Yevgen Matusevych , Sharon Goldwater

Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue et al., 2022). However, these works mainly focus on reporting…

Computation and Language · Computer Science 2022-10-14 Jimin Sun , Patrick Fernandes , Xinyi Wang , Graham Neubig

Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Zehan Li , Yan Yang , Xueqing Li , Jian Kang , Xiao-Lei Zhang , Jie Li