The RoyalFlush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Jingguang, Ye, Shuaishuai, Chen, Shunfei, Xiang, Yang, Yin, Zhaohui, Hu, Xinhui, Xu, Xinkang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914789322653696
author Tian, Jingguang
Ye, Shuaishuai
Chen, Shunfei
Xiang, Yang
Yin, Zhaohui
Hu, Xinhui
Xu, Xinkang
author_facet Tian, Jingguang
Ye, Shuaishuai
Chen, Shunfei
Xiang, Yang
Yin, Zhaohui
Hu, Xinhui
Xu, Xinkang
contents This paper presents our system submission for the In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge, which focuses on speaker diarization and speech recognition in complex multi-speaker scenarios. To address these challenges, we develop end-to-end speaker diarization models that notably decrease the diarization error rate (DER) by 49.58\% compared to the official baseline on the development set. For speech recognition, we utilize self-supervised learning representations to train end-to-end ASR models. By integrating these models, we achieve a character error rate (CER) of 16.93\% on the track 1 evaluation set, and a concatenated minimum permutation character error rate (cpCER) of 25.88\% on the track 2 evaluation set.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05498
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The RoyalFlush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge
Tian, Jingguang
Ye, Shuaishuai
Chen, Shunfei
Xiang, Yang
Yin, Zhaohui
Hu, Xinhui
Xu, Xinkang
Sound
Audio and Speech Processing
This paper presents our system submission for the In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge, which focuses on speaker diarization and speech recognition in complex multi-speaker scenarios. To address these challenges, we develop end-to-end speaker diarization models that notably decrease the diarization error rate (DER) by 49.58\% compared to the official baseline on the development set. For speech recognition, we utilize self-supervised learning representations to train end-to-end ASR models. By integrating these models, we achieve a character error rate (CER) of 16.93\% on the track 1 evaluation set, and a concatenated minimum permutation character error rate (cpCER) of 25.88\% on the track 2 evaluation set.
title The RoyalFlush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2405.05498