End-to-End Speaker-Dependent Voice Activity Detection
This addresses the problem of accurately detecting only target speaker speech in noisy or multi-speaker environments for applications like ASR and speaker recognition, representing an incremental improvement over existing methods.
The paper tackles speaker-dependent voice activity detection (SDVAD) by proposing an end-to-end neural network that incorporates speaker identity, achieving significantly better performance than traditional VAD/SV systems in terms of frame accuracy and F-score on a Switchboard-based dataset.
Voice activity detection (VAD) is an essential pre-processing step for tasks such as automatic speech recognition (ASR) and speaker recognition. A basic goal is to remove silent segments within an audio, while a more general VAD system could remove all the irrelevant segments such as noise and even unwanted speech from non-target speakers. We define the task, which only detects the speech from the target speaker, as speaker-dependent voice activity detection (SDVAD). This task is quite common in real applications and usually implemented by performing speaker verification (SV) on audio segments extracted from VAD. In this paper, we propose an end-to-end neural network based approach to address this problem, which explicitly takes the speaker identity into the modeling process. Moreover, inference can be performed in an online fashion, which leads to low system latency. Experiments are carried out on a conversational telephone dataset generated from the Switchboard corpus. Results show that our proposed online approach achieves significantly better performance than the usual VAD/SV system in terms of both frame accuracy and F-score. We also used our previously proposed segment-level metric for a more comprehensive analysis.