Acoustic modeling for Overlapping Speech Recognition: JHU Chime-5 Challenge System
Abstrak
This paper summarizes our acoustic modeling efforts in the Johns Hopkins University speech recognition system for the CHiME-5 challenge to recognize highly-overlapped dinner party speech recorded by multiple microphone arrays. We explore data augmentation approaches, neural network architectures, front-end speech dereverberation, beamforming and robust i-vector extraction with comparisons of our in-house implementations and publicly available tools. We finally achieved a word error rate of 69.4% on the development set, which is a 11.7% absolute improvement over the previous baseline of 81.1%, and release this improved baseline with refined techniques/tools as an advanced CHiME-5 recipe.
Topik & Kata Kunci
Penulis (6)
Vimal Manohar
Szu-Jui Chen
Zhiqi Wang
Yusuke Fujita
Shinji Watanabe
Sanjeev Khudanpur
Akses Cepat
- Tahun Terbit
- 2024
- Bahasa
- en
- Sumber Database
- arXiv
- Akses
- Open Access ✓