English
Related papers

Related papers: Token-Level Serialized Output Training for Joint S…

200 papers

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-06 Matthew Wiesner , Adithya Renduchintala , Shinji Watanabe , Chunxi Liu , Najim Dehak , Sanjeev Khudanpur

With the surge of online meetings, it has become more critical than ever to provide high-quality speech audio and live captioning under various noise conditions. However, most monaural speech enhancement (SE) models introduce processing…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-08 Sefik Emre Eskimez , Xiaofei Wang , Min Tang , Hemin Yang , Zirun Zhu , Zhuo Chen , Huaming Wang , Takuya Yoshioka

For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then translate with machine translation (MT). A major cause of the performance gap is…

Computation and Language · Computer Science 2019-10-23 Juan Pino , Liezl Puzon , Jiatao Gu , Xutai Ma , Arya D. McCarthy , Deepak Gopinath

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models…

Audio and Speech Processing · Electrical Eng. & Systems 2018-02-16 Shubham Toshniwal , Tara N. Sainath , Ron J. Weiss , Bo Li , Pedro Moreno , Eugene Weinstein , Kanishka Rao

Transducer neural networks have emerged as the mainstream approach for streaming automatic speech recognition (ASR), offering state-of-the-art performance in balancing accuracy and latency. In the conventional framework, streaming…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-27 Hyeonseung Lee , Ji Won Yoon , Sungsoo Kim , Nam Soo Kim

Although end-to-end (E2E) automatic speech recognition (ASR) has shown state-of-the-art recognition accuracy, it tends to be implicitly biased towards the training data distribution which can degrade generalisation. This paper proposes a…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-28 Keqi Deng , Philip C. Woodland

Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…

Computation and Language · Computer Science 2020-05-26 Danni Liu , Jan Niehues , Gerasimos Spanakis

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the previous work on…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-12 Ilya Sklyar , Anna Piunova , Christian Osendorfer

Automatic speech recognition (ASR) has progressed significantly in recent years due to the emergence of large-scale datasets and the self-supervised learning (SSL) paradigm. However, as its counterpart problem in the singing domain, the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-18 Longshen Ou , Xiangming Gu , Ye Wang

Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, fully end-to-end model that performs…

Computation and Language · Computer Science 2026-03-13 Roman Koshkin , Jeon Haesung , Lianbo Liu , Hao Shi , Mengjie Zhao , Yusuke Fujita , Yui Sudo

We present JOIST, an algorithm to train a streaming, cascaded, encoder end-to-end (E2E) model with both speech-text paired inputs, and text-only unpaired inputs. Unlike previous works, we explore joint training with both modalities, rather…

Computation and Language · Computer Science 2022-10-17 Tara N. Sainath , Rohit Prabhavalkar , Ankur Bapna , Yu Zhang , Zhouyuan Huo , Zhehuai Chen , Bo Li , Weiran Wang , Trevor Strohman

Low-resource automatic speech recognition (ASR) continues to pose significant challenges, primarily due to the limited availability of transcribed data for numerous languages. While a wealth of spoken content is accessible in television…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-26 Cheng-Yeh Yang , Chien-Chun Wang , Li-Wei Chen , Hung-Shin Lee , Hsin-Min Wang , Berlin Chen

Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-09 Yuke Lin , Ming Cheng , Ze Li , Beilong Tang , Ming Li

Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such…

Sound · Computer Science 2026-02-05 Takanori Ashihara , Shota Horiguchi , Kohei Matsuura , Tsubasa Ochiai , Marc Delcroix

Speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a…

Computation and Language · Computer Science 2022-04-18 Qianqian Dong , Mingxuan Wang , Hao Zhou , Shuang Xu , Bo Xu , Lei Li

Automatic Speech Recognition (ASR) is a technology that converts spoken words into text, facilitating interaction between humans and machines. One of the most common applications of ASR is Speech-To-Text (STT) technology, which simplifies…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-02 Jaeyoung Huh , Sangjoon Park , Jeong Eun Lee , Jong Chul Ye

Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-21 Muqiao Yang , Naoyuki Kanda , Xiaofei Wang , Jian Wu , Sunit Sivasankaran , Zhuo Chen , Jinyu Li , Takuya Yoshioka

Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-29 Youness Dkhissi , Valentin Vielzeuf , Elys Allesiardo , Anthony Larcher

New-age conversational agent systems perform both speech emotion recognition (SER) and automatic speech recognition (ASR) using two separate and often independent approaches for real-world application in noisy environments. In this paper,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-29 Lokesh Bansal , S. Pavankumar Dubagunta , Malolan Chetlur , Pushpak Jagtap , Aravind Ganapathiraju

Speech-to-text translation pertains to the task of converting speech signals in a language to text in another language. It finds its application in various domains, such as hands-free communication, dictation, video lecture transcription,…

Computation and Language · Computer Science 2024-06-11 Nivedita Sethiya , Chandresh Kumar Maurya