# Demystifying TasNet: A Dissecting Approach

arXiv: https://arxiv.org/abs/1911.08895 · HTML: https://mlsanity.com/paper/1911.08895/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [On loss functions and evaluation metrics for music source separation](https://mlsanity.com/paper/2202.07968/) (2022)
- [Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes](https://mlsanity.com/paper/2206.11703/) (2022)
- [Phase-Aware Deep Speech Enhancement: It's All About The Frame Length](https://mlsanity.com/paper/2203.16222/) (2022)
- [On permutation invariant training for speech source separation](https://mlsanity.com/paper/2102.04945/) (2021)
- [Mixture Encoder for Joint Speech Separation and Recognition](https://mlsanity.com/paper/2306.12173/) (2023)
- [Deep neural network techniques for monaural speech enhancement: state of the art analysis](https://mlsanity.com/paper/2212.00369/) (2022)
- [Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet](https://mlsanity.com/paper/2402.17701/) (2024)
- [Reverberation as Supervision for Speech Separation](https://mlsanity.com/paper/2211.08303/) (2022)
- [Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement](https://mlsanity.com/paper/2408.17358/) (2024)
- [Knowing When to Quit: Probabilistic Early Exits for Speech Separation](https://mlsanity.com/paper/2507.09768/) (2025)
- [Integrating Uncertainty into Neural Network-based Speech Enhancement](https://mlsanity.com/paper/2305.08744/) (2023)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)

## Abstract (arXiv)

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 it is this criterion which contributes most reliable to the performance advantage of TasNet. Finally, we critically assess which gains in a noise-free single channel environment generalize to more realistic reverberant conditions.