Mohan Shi

end-to-end model (2) automatic speech recognition (2) speech separation (1) speech recognition (1) neural machine translation (1) speaker verification (1) speaker diarization (1) low latency (1) speech translation (1) semantic loss (1) cascaded architecture (1) cascaded system (1) voice activity detection (1) reverberant speech (1) far-field speech (1) punctuation prediction (1) low-latency segmentation (1) speech interaction (1) multi-talker speech (1) context-aware modeling (1)