Overlap-Adaptive Hybrid Speaker Diarization and ASR-Aware Observation Addition for MISP 2025 Challenge

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Shangkun, Du, Yuxuan, Yang, Jingwen, Zhang, Dejun, Jia, Xupeng, Deng, Jing, Kang, Jintao, Zheng, Rong
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918037169373184
author Huang, Shangkun
Du, Yuxuan
Yang, Jingwen
Zhang, Dejun
Jia, Xupeng
Deng, Jing
Kang, Jintao
Zheng, Rong
author_facet Huang, Shangkun
Du, Yuxuan
Yang, Jingwen
Zhang, Dejun
Jia, Xupeng
Deng, Jing
Kang, Jintao
Zheng, Rong
contents This paper presents the system developed to address the MISP 2025 Challenge. For the diarization system, we proposed a hybrid approach combining a WavLM end-to-end segmentation method with a traditional multi-module clustering technique to adaptively select the appropriate model for handling varying degrees of overlapping speech. For the automatic speech recognition (ASR) system, we proposed an ASR-aware observation addition method that compensates for the performance limitations of Guided Source Separation (GSS) under low signal-to-noise ratio conditions. Finally, we integrated the speaker diarization and ASR systems in a cascaded architecture to address Track 3. Our system achieved character error rates (CER) of 9.48% on Track 2 and concatenated minimum permutation character error rate (cpCER) of 11.56% on Track 3, ultimately securing first place in both tracks and thereby demonstrating the effectiveness of the proposed methods in real-world meeting scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22013
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Overlap-Adaptive Hybrid Speaker Diarization and ASR-Aware Observation Addition for MISP 2025 Challenge
Huang, Shangkun
Du, Yuxuan
Yang, Jingwen
Zhang, Dejun
Jia, Xupeng
Deng, Jing
Kang, Jintao
Zheng, Rong
Sound
Audio and Speech Processing
This paper presents the system developed to address the MISP 2025 Challenge. For the diarization system, we proposed a hybrid approach combining a WavLM end-to-end segmentation method with a traditional multi-module clustering technique to adaptively select the appropriate model for handling varying degrees of overlapping speech. For the automatic speech recognition (ASR) system, we proposed an ASR-aware observation addition method that compensates for the performance limitations of Guided Source Separation (GSS) under low signal-to-noise ratio conditions. Finally, we integrated the speaker diarization and ASR systems in a cascaded architecture to address Track 3. Our system achieved character error rates (CER) of 9.48% on Track 2 and concatenated minimum permutation character error rate (cpCER) of 11.56% on Track 3, ultimately securing first place in both tracks and thereby demonstrating the effectiveness of the proposed methods in real-world meeting scenarios.
title Overlap-Adaptive Hybrid Speaker Diarization and ASR-Aware Observation Addition for MISP 2025 Challenge
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2505.22013