VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
arXiv: Audio and Speech Processing, Volume abs/1810.04826, 2019, Pages 2728-2732.
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram maskin...More
PPT (Upload PPT)