The NPU-ASLP System for The ISCSLP 2022 Magichub Code-Swiching ASR Challenge

Yuhao Liang, Peikun Chen, Fan Yu, Xinfa Zhu, Tianyi Xu, Yingying Gao, Lei Xie

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes our NPU-ASLP system submitted to the ISCSLP 2022 Magichub Code-Switching ASR Challenge. In this challenge, we first explore several popular end-to-end multilingual ASR architectures and training strategies, including bi-encoder, language-aware encoder (LAE) and mixture of experts (MoE). To improve our system's language modeling ability, we further attempt the internal language model as well as the long context language model. Given the limited training data in the challenge, we further investigate data augmentation strategies, including speed perturbation, pitch shifting, speech codec, SpecAugment and synthetic data from text-to-speech (TTS). Finally, we explore ROVER-based score fusion to make full use of complementary hypotheses from different models. Our submitted system achieves 16.87% on mix error rate (MER) on the test set and comes to the 2nd place in the challenge ranking.

Original languageEnglish
Title of host publication2022 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022
EditorsKong Aik Lee, Hung-yi Lee, Yanfeng Lu, Minghui Dong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages532-536
Number of pages5
ISBN (Electronic)9798350397963
DOIs
StatePublished - 2022
Event13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022 - Singapore, Singapore
Duration: 11 Dec 202214 Dec 2022

Publication series

Name2022 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022

Conference

Conference13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022
Country/TerritorySingapore
CitySingapore
Period11/12/2214/12/22

Keywords

  • Automatic Speech Recognition
  • Code-Switching
  • Data Augmentation

Fingerprint

Dive into the research topics of 'The NPU-ASLP System for The ISCSLP 2022 Magichub Code-Swiching ASR Challenge'. Together they form a unique fingerprint.

Cite this