kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Jiaming, Zhao, Shiwan, Liu, Yaqi, Zeng, Wenjia, Chen, Yong, Qin, Yong
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910317433323520
author Zhou, Jiaming
Zhao, Shiwan
Liu, Yaqi
Zeng, Wenjia
Chen, Yong
Qin, Yong
author_facet Zhou, Jiaming
Zhao, Shiwan
Liu, Yaqi
Zeng, Wenjia
Chen, Yong
Qin, Yong
contents The success of retrieval-augmented language models in various natural language processing (NLP) tasks has been constrained in automatic speech recognition (ASR) applications due to challenges in constructing fine-grained audio-text datastores. This paper presents kNN-CTC, a novel approach that overcomes these challenges by leveraging Connectionist Temporal Classification (CTC) pseudo labels to establish frame-level audio-text key-value pairs, circumventing the need for precise ground truth alignments. We further introduce a skip-blank strategy, which strategically ignores CTC blank frames, to reduce datastore size. kNN-CTC incorporates a k-nearest neighbors retrieval mechanism into pre-trained CTC ASR systems, achieving significant improvements in performance. By incorporating a k-nearest neighbors retrieval mechanism into pre-trained CTC ASR systems and leveraging a fine-grained, pruned datastore, kNN-CTC consistently achieves substantial improvements in performance under various experimental settings. Our code is available at https://github.com/NKU-HLT/KNN-CTC.
format Preprint
id arxiv_https___arxiv_org_abs_2312_13560
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
Zhou, Jiaming
Zhao, Shiwan
Liu, Yaqi
Zeng, Wenjia
Chen, Yong
Qin, Yong
Sound
Audio and Speech Processing
The success of retrieval-augmented language models in various natural language processing (NLP) tasks has been constrained in automatic speech recognition (ASR) applications due to challenges in constructing fine-grained audio-text datastores. This paper presents kNN-CTC, a novel approach that overcomes these challenges by leveraging Connectionist Temporal Classification (CTC) pseudo labels to establish frame-level audio-text key-value pairs, circumventing the need for precise ground truth alignments. We further introduce a skip-blank strategy, which strategically ignores CTC blank frames, to reduce datastore size. kNN-CTC incorporates a k-nearest neighbors retrieval mechanism into pre-trained CTC ASR systems, achieving significant improvements in performance. By incorporating a k-nearest neighbors retrieval mechanism into pre-trained CTC ASR systems and leveraging a fine-grained, pruned datastore, kNN-CTC consistently achieves substantial improvements in performance under various experimental settings. Our code is available at https://github.com/NKU-HLT/KNN-CTC.
title kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2312.13560