Saved in:
Bibliographic Details
Main Authors: Yang, Haoyuan, Zhang, Yue, Jing, Liqiang, Hansen, John H. L.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.07323
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914391859920896
author Yang, Haoyuan
Zhang, Yue
Jing, Liqiang
Hansen, John H. L.
author_facet Yang, Haoyuan
Zhang, Yue
Jing, Liqiang
Hansen, John H. L.
contents Automatic Speech Recognition (ASR) has achieved remarkable success with deep learning, driving advancements in conversational artificial intelligence, media transcription, and assistive technologies. However, ASR systems still struggle in complex environments such as TV series, where multiple speakers, overlapping speech, domain-specific terminology, and long-range contextual dependencies pose significant challenges to transcription accuracy. Existing approaches fail to explicitly leverage the rich temporal and contextual information available in the video. To address this limitation, we propose a Video-Guided Post-ASR Correction (VPC) framework that uses a Video-Large Multimodal Model (VLMM) to capture video context and refine ASR outputs. Evaluations on a TV-series benchmark show that our method consistently improves transcription accuracy in complex multimedia environments.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07323
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Speech Recognition on TV Series with Video-guided Post-ASR Correction
Yang, Haoyuan
Zhang, Yue
Jing, Liqiang
Hansen, John H. L.
Sound
Artificial Intelligence
Audio and Speech Processing
Automatic Speech Recognition (ASR) has achieved remarkable success with deep learning, driving advancements in conversational artificial intelligence, media transcription, and assistive technologies. However, ASR systems still struggle in complex environments such as TV series, where multiple speakers, overlapping speech, domain-specific terminology, and long-range contextual dependencies pose significant challenges to transcription accuracy. Existing approaches fail to explicitly leverage the rich temporal and contextual information available in the video. To address this limitation, we propose a Video-Guided Post-ASR Correction (VPC) framework that uses a Video-Large Multimodal Model (VLMM) to capture video context and refine ASR outputs. Evaluations on a TV-series benchmark show that our method consistently improves transcription accuracy in complex multimedia environments.
title Speech Recognition on TV Series with Video-guided Post-ASR Correction
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2506.07323