End-to-end Speech Separation With Unfolded Iterative Phase Reconstruction

Abstract

This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within a deep network. Previous approaches, rather than computing a loss on the reconstructed signal, used a surrogate loss based on the target STFT magnitudes. This ignores reconstruction error introduced by phase inconsistency. In our approach, the loss function is directly defined on the reconstructed signals, which are optimized for best separation. In addition, we train through unfolded iterations of a phase reconstruction algorithm, represented as a series of STFT and inverse STFT layers. While mask values are typically limited to lie between zero and one for approaches using the mixture phase for reconstruction, this limitation is less relevant if the estimated magnitudes are to be used together with phase reconstruction. We thus propose several nov

Stats

• citations99
• S2 citations—
• github stars0
• HF likes0
• heat score15.00
• arxiv keywang2018end

Related papers

• Mask-dependent Phase Estimation For Monaural Speaker Separation (2019)6.34
• Deep Learning Based Phase Reconstruction For Speaker Separation: A Trigonometric Perspective (2018)13.34
• End-to-end Multi-channel Speech Separation (2019)0.00
• End-to-end Networks For Supervised Single-channel Speech Separation (2018)0.00
• Multi-channel Narrow-band Deep Speech Separation With Full-band Permutation Invariant Training (2021)9.41
• Deep Attractor Network For Single-microphone Speaker Separation (2016)17.88
• End-to-end Training Of Time Domain Audio Separation And Recognition (2019)10.35
• Conv-tasnet: Surpassing Ideal Time-frequency Magnitude Masking For Speech Separation (2018)24.08