Two-stage Model And Optimal SI-SNR For Monaural Multi-speaker Speech Separation In Noisy Environment

Abstract

In daily listening environments, speech is always distorted by background noise, room reverberation and interference speakers. With the developing of deep learning approaches, much progress has been performed on monaural multi-speaker speech separation. Nevertheless, most studies in this area focus on a simple problem setup of laboratory environment, which background noises and room reverberations are not considered. In this paper, we propose a two-stage model based on conv-TasNet to deal with the notable effects of noises and interference speakers separately, where enhancement and separation are conducted sequentially using deep dilated temporal convolutional networks (TCN). In addition, we develop a new objective function named optimal scale-invariant signal-noise ratio (OSI-SNR), which are better than original SI-SNR at any circumstances. By jointly training the two-stage model with OSI-SNR, our algorithm outperforms one-stage separation baselines substantially.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyma2020two

Related papers

• Real-time Speech Enhancement And Separation With A Unified Deep Neural Network For Single/dual Talker Scenarios (2023)2.26
• A Multi-stage Triple-path Method For Speech Separation In Noisy And Reverberant Environments (2023)2.26
• Deformable Temporal Convolutional Networks For Monaural Noisy Reverberant Speech Separation (2022)8.09
• Audio-visual Speech Separation And Dereverberation With A Two-stage Multimodal Network (2019)12.47
• On Time Domain Conformer Models For Monaural Speech Separation In Noisy Reverberant Acoustic Environments (2023)5.84
• Unifying Speech Enhancement And Separation With Gradient Modulation For End-to-end Noise-robust Speech Separation (2023)0.00
• A Two-stage Speaker Extraction Algorithm Under Adverse Acoustic Conditions Using A Single-microphone (2023)0.00
• An Enhanced Conv-tasnet Model For Speech Separation Using A Speaker Distance-based Loss Function (2022)0.00