# On The Compensation Between Magnitude and Phase in Speech Separation

arXiv: https://arxiv.org/abs/2108.05470 · HTML: https://mlsanity.com/paper/2108.05470/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2021.

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

- [CMGAN: Conformer-based Metric GAN for Speech Enhancement](https://mlsanity.com/paper/2203.15149/) (2022)
- [CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement](https://mlsanity.com/paper/2209.11112/) (2022)
- [Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement](https://mlsanity.com/paper/2110.06467/) (2021)
- [A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation](https://mlsanity.com/paper/2309.02539/) (2023)
- [Phase-Aware Deep Speech Enhancement: It's All About The Frame Length](https://mlsanity.com/paper/2203.16222/) (2022)
- [BASEN: Time-Domain Brain-Assisted Speech Enhancement Network with Convolutional Cross Attention in Multi-talker Conditions](https://mlsanity.com/paper/2305.09994/) (2023)
- [A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement](https://mlsanity.com/paper/2505.24576/) (2025)
- [Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations](https://mlsanity.com/paper/2507.21448/) (2025)
- [A Survey of Deep Learning for Complex Speech Spectrograms](https://mlsanity.com/paper/2505.08694/) (2025)
- [A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model](https://mlsanity.com/paper/2505.13843/) (2025)
- [Real-Time System for Audio-Visual Target Speech Enhancement](https://mlsanity.com/paper/2509.20741/) (2025)
- [DBHN-Net: Dual-Branch Hybrid Neural Network For Low-Complexity Monaural Speech Enhancement](https://mlsanity.com/paper/2606.05911/) (2026)

## Abstract (arXiv)

Deep neural network (DNN) based end-to-end optimization in the complex time-frequency (T-F) domain or time domain has shown considerable potential in monaural speech separation. Many recent studies optimize loss functions defined solely in the time or complex domain, without including a loss on magnitude. Although such loss functions typically produce better scores if the evaluation metrics are objective time-domain metrics, they however produce worse scores on speech quality and intelligibility metrics and usually lead to worse speech recognition performance, compared with including a loss on magnitude. While this phenomenon has been experimentally observed by many studies, it is often not accurately explained and there lacks a thorough understanding on its fundamental cause. This paper provides a novel view from the perspective of the implicit compensation between estimated magnitude and phase. Analytical results based on monaural speech separation and robust automatic speech recognition (ASR) tasks in noisy-reverberant conditions support the validity of our view.