ICASSP 2023accepted0 citations
The NIO System for Audio-Visual Diarization and Recognition in MISP Challenge 2022
Gaopeng Xu, Xianliang Wang, Sang Wang, Junfeng Yuan, Wei Guo, Wei Li, Jie Gao
Abstract
This paper describes NIO system for audio-visual diarization and recognition in the Multimodal Information Based Speech Processing (MISP) Challenge 2022. In our system, we proposed combining end-to-end audio-visual neural speaker diarization model and Channel-wise Av-fusion encoder with speaker signature for multi-channel audio-visual speech diarization and recognition. Our system reduces the concatenated minimum permutation character error rate(cpCER) by 34.36% absolute compared to the baseline in track 2.
BibTeX
@inproceedings{icassp2023_theniosystemfora,
title = {The NIO System for Audio-Visual Diarization and Recognition in MISP Challenge 2022},
author = {Gaopeng Xu and Xianliang Wang and Sang Wang and Junfeng Yuan and Wei Guo and Wei Li and Jie Gao},
booktitle = {ICASSP 2023},
year = {2023}
}