WAVLab
affiliated with @ LTI/CMU.
This is Watanabe’s Audio and Voice (WAV) Lab at the Language Technologies Institute of Carnegie Mellon University. Our research interests include automatic speech recognition, speech enhancement, spoken language understanding, and machine learning for speech and language processing.
selected publications
- SD CSLA review of speaker diarization: Recent advances with deep learningComputer Speech & Language 2022
- ST ACLESPnet-ST: All-in-One Speech Translation ToolkitIn Proceedings of the Annual Meeting of the Association for Computational Linguistics 2020