English
Related papers

Related papers: A Likelihood Ratio based Domain Adaptation Method …

200 papers

Contextual biasing refers to the problem of biasing the automatic speech recognition (ASR) systems towards rare entities that are relevant to the specific user or application scenarios. We propose algorithms for contextual biasing based on…

End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a two-pass model has been proposed to rescore streamed…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-19 Ke Hu , Tara N. Sainath , Ruoming Pang , Rohit Prabhavalkar

The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption,…

Sound · Computer Science 2022-09-27 Long Mai , Julie Carson-Berndsen

Sequence-to-sequence (S2S) modeling is becoming a popular paradigm for automatic speech recognition (ASR) because of its ability to jointly optimize all the conventional ASR components in an end-to-end (E2E) fashion. This report…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-30 Aswin Shanmugam Subramanian , Xiaofei Wang , Shinji Watanabe , Toru Taniguchi , Dung Tran , Yuya Fujita

OpenAI's Whisper Automated Speech Recognition model excels in generalizing across diverse datasets and domains. However, this broad adaptability can lead to diminished performance in tasks requiring recognition of specific vocabularies.…

Artificial Intelligence · Computer Science 2025-08-12 Vishakha Lall , Yisi Liu

Automatic speech recognition (ASR) systems often encounter difficulties in accurately recognizing rare words, leading to errors that can have a negative impact on downstream tasks such as keyword spotting, intent detection, and text…

Artificial Intelligence · Computer Science 2023-10-10 Jiajun He , Zekun Yang , Tomoki Toda

The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition. However, up until now, state-of-the-art neural network-based time domain source…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-14 Thilo von Neumann , Keisuke Kinoshita , Lukas Drude , Christoph Boeddeker , Marc Delcroix , Tomohiro Nakatani , Reinhold Haeb-Umbach

The goal of spoken language understanding (SLU) systems is to determine the meaning of the input speech signal, unlike speech recognition which aims to produce verbatim transcripts. Advances in end-to-end (E2E) speech modeling have made it…

Computation and Language · Computer Science 2022-01-31 Hong-Kwang J. Kuo , Zoltan Tuske , Samuel Thomas , Brian Kingsbury , George Saon

The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due to the noise, etc. In this case, the acoustic information can be less reliable.…

Computation and Language · Computer Science 2020-11-03 Dominique Fohr , Irina Illina

Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data. While recently developed end-to-end methods largely simplify the modeling pipelines, they still suffer from the data…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Yang Chen , Weiran Wang , I-Fan Chen , Chao Wang

In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-learning-based image-to-image translation technique to…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-15 Jong-Hyeon Park , Myungwoo Oh , Hyung-Min Park

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement algorithms. However, speech enhancement has not been established as an effective frontend for robust automatic speech recognition (ASR) in…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-22 Yufeng Yang , Ashutosh Pandey , DeLiang Wang

In this paper we introduce a recurrent neural network (RNN) based variational autoencoder (VAE) model with a new constrained loss function that can generate more meaningful electroencephalography (EEG) features from raw EEG features to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-05 Gautam Krishna , Co Tran , Mason Carnahan , Ahmed Tewfik

In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are…

Computation and Language · Computer Science 2016-06-29 Kyuyeon Hwang , Wonyong Sung

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transformer has a drawback in…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-17 Emiru Tsunoo , Yosuke Kashiwagi , Toshiyuki Kumakura , Shinji Watanabe

We propose a method for zero-resource domain adaptation of DNN acoustic models, for use in low-resource situations where the only in-language training data available may be poorly matched to the intended target domain. Our method uses a…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-31 Alberto Abad , Peter Bell , Andrea Carmantini , Steve Renals

Automatic speech recognition (ASR) has become increasingly ubiquitous on modern edge devices. Past work developed streaming End-to-End (E2E) all-neural speech recognizers that can run compactly on edge devices. However, E2E ASR models are…

Computation and Language · Computer Science 2021-07-13 Dilin Wang , Yuan Shangguan , Haichuan Yang , Pierce Chuang , Jiatong Zhou , Meng Li , Ganesh Venkatesh , Ozlem Kalinli , Vikas Chandra

End-to-end automatic speech recognition (E2E-ASR) has the potential to improve performance, but a specific issue that needs to be addressed is the difficulty it has in handling enharmonic words: named entities (NEs) with the same…

Sound · Computer Science 2023-05-30 Yui Sudo , Kazuya Hata , Kazuhiro Nakadai

Contextual biasing improves rare word recognition of ASR models by prioritizing the output of rare words during decoding. A common approach is Trie-based biasing, which gives "bonus scores" to partial hypothesis (e.g. "Bon") that may lead…

Computation and Language · Computer Science 2025-09-12 Chin Yuen Kwok , Jia Qi yip

End-to-end models in general, and Recurrent Neural Network Transducer (RNN-T) in particular, have gained significant traction in the automatic speech recognition community in the last few years due to their simplicity, compactness, and…

Computation and Language · Computer Science 2020-11-17 Duc Le , Gil Keren , Julian Chan , Jay Mahadeokar , Christian Fuegen , Michael L. Seltzer