Demystifying Tasnet: A Dissecting Approach

Abstract

In recent years time domain speech separation has excelled over frequency domain separation in single channel scenarios and noise-free environments. In this paper we dissect the gains of the time-domain audio separation network (TasNet) approach by gradually replacing components of an utterance-level permutation invariant training (u-PIT) based separation system in the frequency domain until the TasNet system is reached, thus blending components of frequency domain approaches with those of time domain approaches. Some of the intermediate variants achieve comparable signal-to-distortion ratio (SDR) gains to TasNet, but retain the advantage of frequency domain processing: compatibility with classic signal processing tools such as frequency-domain beamforming and the human interpretability of the masks. Furthermore, we show that the scale invariant signal-to-distortion ratio (si-SDR) criterion used as loss function in TasNet is related to a logarithmic mean square error criterion and that

Stats

• citations40
• S2 citations—
• github stars0
• HF likes0
• heat score12.10
• arxiv keyheitkaemper2019demystifying

Related papers

• Tasnet: Time-domain Audio Separation Network For Real-time, Single-channel Speech Separation (2017)20.16
• Beam-guided Tasnet: An Iterative Speech Separation Framework With Multi-channel Output (2021)9.76
• Conv-tasnet: Surpassing Ideal Time-frequency Magnitude Masking For Speech Separation (2018)24.08
• X-tasnet: Robust And Accurate Time-domain Speaker Extraction Network (2020)10.48
• A Comprehensive Study Of Speech Separation: Spectrogram Vs Waveform Separation (2019)13.44
• Toward Speech Separation In The Pre-cocktail Party Problem With Tastas (2020)0.00
• Speech Separation Based On Multi-stage Elaborated Dual-path Deep Bilstm With Auxiliary Identity Loss (2020)9.77
• Time Domain Audio Visual Speech Separation (2019)14.62