Single Channel Voice Separation for Unknown Number of Speakers Under Reverberant and Noisy Settings
By Shlomo E. Chazan, Lior Wolf, Eliya Nachmani, Yossi Adi. 2020
32 citations recorded by the source corpus.
We present a unified network for voice separation of an unknown number of speakers. The proposed approach is composed of several separation heads optimized together with a speaker classification branch. The separation is carried out in the time domain, together with parameter sharing between all separation heads. The classification branch estimates the number of speakers while each head is specialized in separating a different number of speakers. We evaluate the proposed model under both clean and noisy reverberant settings. Results suggest that the proposed approach is superior to the baseline model by a significant margin. Additionally, we present a new noisy and reverberant dataset of up to five different speakers speaking simultaneously.
Subfields: Speech & Audio, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Speech & Audio
- Yossi Adi
- Wei-Ning Hsu
- Gabriel Synnaeve
- Jade Copet
- Bowen Shi
- Alexandre D'efossez
- Tal Remez
- Jacob Donley
In Signal Processing
- Yossi Adi
- Wei-Ning Hsu
- Gabriel Synnaeve
- Bowen Shi
- Jade Copet
- Tal Remez
- Alexandre D'efossez
- Jacob Donley
Citations in the corpus
- High Fidelity Neural Audio Compression (2022, methodology): “For objective metrics, we use ViSQOL (Hines et al., 2012; Chinen et al., 2020) 2 , together with the Scale-Invariant Signal-to-Noise Ration (SI-SNR) (Luo & Mesgarani, 2019; Nachmani et al., 2020; Chazan et al., 2021).”
- A Metaverse: Taxonomy, Components, Applications, and Open Challenges (2022, unknown): “Chazan et al. [258] presented an integrated network for speech separation of an unknown number of speakers and presented a noise and reverberation dataset for five speakers.”
- ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement (2022, methodology): “Hence, previous studies directly predict spectrogram [36,38] or waveform [7,37,39] as ˆ x a = f (˜ x a , x v ) and optimize the model with regression and adversarial losses.”