Naoyuki Kanda

On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer

2021

Hybrid Autoregressive Transducer (HAT) is a recently proposed end-to-end acoustic model that extends the standard Recurrent Neural Network Transducer (RNN-T) for the purpose of the external language model (LM) fusion.In HAT, the blank probability and …

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 …