Saved in:
Bibliographic Details
Main Authors: Xu, Yaoxun, Song, Xingchen, Wu, Zhiyong, Wu, Di, Peng, Zhendong, Zhang, Binbin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.04325
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910560405159936
author Xu, Yaoxun
Song, Xingchen
Wu, Zhiyong
Wu, Di
Peng, Zhendong
Zhang, Binbin
author_facet Xu, Yaoxun
Song, Xingchen
Wu, Zhiyong
Wu, Di
Peng, Zhendong
Zhang, Binbin
contents In automatic speech recognition, subsampling is essential for tackling diverse scenarios. However, the inadequacy of a single subsampling rate to address various real-world situations often necessitates training and deploying multiple models, consequently increasing associated costs. To address this issue, we propose HydraFormer, comprising HydraSub, a Conformer-based encoder, and a BiTransformer-based decoder. HydraSub encompasses multiple branches, each representing a distinct subsampling rate, allowing for the flexible selection of any branch during inference based on the specific use case. HydraFormer can efficiently manage different subsampling rates, significantly reducing training and deployment expenses. Experiments on AISHELL-1 and LibriSpeech datasets reveal that HydraFormer effectively adapts to various subsampling rates and languages while maintaining high recognition performance. Additionally, HydraFormer showcases exceptional stability, sustaining consistent performance under various initialization conditions, and exhibits robust transferability by learning from pretrained single subsampling rate automatic speech recognition models\footnote{Model code and scripts: https://github.com/HydraFormer/hydraformer}.
format Preprint
id arxiv_https___arxiv_org_abs_2408_04325
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HydraFormer: One Encoder For All Subsampling Rates
Xu, Yaoxun
Song, Xingchen
Wu, Zhiyong
Wu, Di
Peng, Zhendong
Zhang, Binbin
Audio and Speech Processing
Computation and Language
In automatic speech recognition, subsampling is essential for tackling diverse scenarios. However, the inadequacy of a single subsampling rate to address various real-world situations often necessitates training and deploying multiple models, consequently increasing associated costs. To address this issue, we propose HydraFormer, comprising HydraSub, a Conformer-based encoder, and a BiTransformer-based decoder. HydraSub encompasses multiple branches, each representing a distinct subsampling rate, allowing for the flexible selection of any branch during inference based on the specific use case. HydraFormer can efficiently manage different subsampling rates, significantly reducing training and deployment expenses. Experiments on AISHELL-1 and LibriSpeech datasets reveal that HydraFormer effectively adapts to various subsampling rates and languages while maintaining high recognition performance. Additionally, HydraFormer showcases exceptional stability, sustaining consistent performance under various initialization conditions, and exhibits robust transferability by learning from pretrained single subsampling rate automatic speech recognition models\footnote{Model code and scripts: https://github.com/HydraFormer/hydraformer}.
title HydraFormer: One Encoder For All Subsampling Rates
topic Audio and Speech Processing
Computation and Language
url https://arxiv.org/abs/2408.04325