English
Related papers

Related papers: Distilling the Knowledge of BERT for CTC-based ASR

200 papers

In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to…

Computation and Language · Computer Science 2023-12-18 Tzu-Ting Yang , Hsin-Wei Wang , Berlin Chen

Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in…

Computation and Language · Computer Science 2021-01-27 Hyunjin Choi , Judong Kim , Seongho Joe , Youngjune Gwon

Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-18 Hexin Liu , Haoyang Zhang , Qiquan Zhang , Xiangyu Zhang , Dongyuan Shi , Eng Siong Chng , Haizhou Li

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

Previous works on emotion recognition in conversation (ERC) follow a two-step paradigm, which can be summarized as first producing context-independent features via fine-tuning pretrained language models (PLMs) and then analyzing contextual…

Computation and Language · Computer Science 2023-01-18 Xiangyu Qin , Zhiyu Wu , Jinshi Cui , Tingting Zhang , Yanran Li , Jian Luan , Bin Wang , Li Wang

Fine-tuned Bidirectional Encoder Representations from Transformers (BERT)-based sequence classification models have proven to be effective for detecting Alzheimer's Disease (AD) from transcripts of human speech. However, previous research…

Computation and Language · Computer Science 2020-11-13 Aparna Balagopalan , Jekaterina Novikova

Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks. Recent works have shown that attention-based models can benefit from more focused attention over local regions.…

Computation and Language · Computer Science 2021-05-25 Zhongli Li , Qingyu Zhou , Chao Li , Ke Xu , Yunbo Cao

This paper presents a speech BERT model to extract embedded prosody information in speech segments for improving the prosody of synthesized speech in neural text-to-speech (TTS). As a pre-trained model, it can learn prosody attributes from…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-15 Liping Chen , Yan Deng , Xi Wang , Frank K. Soong , Lei He

Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from…

Audio and Speech Processing · Electrical Eng. & Systems 2018-01-24 Sibo Tong , Philip N. Garner , Hervé Bourlard

Test-Time Adaptation (TTA) has emerged as a crucial solution to the domain shift challenge, wherein the target environment diverges from the original training environment. A prime exemplification is TTA for Automatic Speech Recognition…

Computation and Language · Computer Science 2024-08-13 Eunseop Yoon , Hee Suk Yoon , John Harvill , Mark Hasegawa-Johnson , Chang D. Yoo

Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models. Both models define a transcription probability by…

Computation and Language · Computer Science 2017-06-07 Liang Lu , Lingpeng Kong , Chris Dyer , Noah A. Smith

Learning an effective speaker representation is crucial for achieving reliable performance in speaker verification tasks. Speech signals are high-dimensional, long, and variable-length sequences containing diverse information at each…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-25 Wei Xia , John H. L. Hansen

CTC compressor can be an effective approach to integrate audio encoders to decoder-only models, which has gained growing interest for different speech applications. In this work, we propose a novel CTC compressor based joint speech and text…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Wei Zhou , Junteng Jia , Leda Sari , Jay Mahadeokar , Ozlem Kalinli

Non-autoregressive mechanisms can significantly decrease inference time for speech transformers, especially when the single step variant is applied. Previous work on CTC alignment-based single step non-autoregressive transformer (CASS-NAT)…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-23 Ruchao Fan , Wei Chu , Peng Chang , Jing Xiao , Abeer Alwan

This paper introduces ASTRA, a novel method for improving Automatic Speech Recognition (ASR) through text injection.Unlike prevailing techniques, ASTRA eliminates the need for sampling to match sequence lengths between speech and text…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-27 Neeraj Gaur , Rohan Agrawal , Gary Wang , Parisa Haghani , Andrew Rosenberg , Bhuvana Ramabhadran

Combination approaches for speech recognition (ASR) systems cover structured sentence-level or word-based merging techniques as well as combination of model scores during beam search. In this work, we compare model combination across…

Sound · Computer Science 2025-08-14 Noureldin Bayoumi , Robin Schmitt , Tina Raissi , Albert Zeyer , Ralf Schlüter , Hermann Ney

The rapid development of neural text-to-speech (TTS) systems enabled its usage in other areas of natural language processing such as automatic speech recognition (ASR) or spoken language translation (SLT). Due to the large number of…

Computation and Language · Computer Science 2024-08-01 Nick Rossenbach , Ralf Schlüter , Sakriani Sakti

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

Computation and Language · Computer Science 2020-11-03 Chao-Wei Huang , Yun-Nung Chen

Spoken conversational question answering (SCQA) requires machines to model complex dialogue flow given the speech utterances and text corpora. Different from traditional text question answering (QA) tasks, SCQA involves audio signal…

Computation and Language · Computer Science 2021-06-25 Chenyu You , Nuo Chen , Yuexian Zou

Neural contextual biasing effectively improves automatic speech recognition (ASR) for crucial phrases within a speaker's context, particularly those that are infrequent in the training data. This work proposes contextual text injection…

Computation and Language · Computer Science 2024-06-12 Zhong Meng , Zelin Wu , Rohit Prabhavalkar , Cal Peyser , Weiran Wang , Nanxin Chen , Tara N. Sainath , Bhuvana Ramabhadran