Wu, Jian

Deploying self-supervised learning in the wild for hybrid automatic speech recognition

2022 · arXiv (Cornell University)

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming End-to-End ASR models. …

Profile-Error-Tolerant Target-Speaker Voice Activity Detection

2023 · arXiv (Cornell University)

Target-Speaker Voice Activity Detection (TS-VAD) utilizes a set of speaker profiles alongside an input audio signal to perform speaker diarization. While its superiority over conventional methods has been demonstrated, the method can suffer from errors …