# Dynamic Acoustic Compensation and Adaptive Focal Training for Personalized Speech Enhancement

arXiv: https://arxiv.org/abs/2211.12097 · HTML: https://mlsanity.com/paper/2211.12097/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [Class Rectification Hard Mining for Imbalanced Deep Learning](https://mlsanity.com/paper/1712.03162/) (2017)
- [ICASSP 2021 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2009.06122/) (2020)
- [FRCRN: Boosting Feature Representation using Frequency Recurrence for Monaural Speech Enhancement](https://mlsanity.com/paper/2206.07293/) (2022)
- [Improving speaker discrimination of target speech extraction with time-domain SpeakerBeam](https://mlsanity.com/paper/2001.08378/) (2020)
- [DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement](https://mlsanity.com/paper/2106.08672/) (2021)
- [On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement](https://mlsanity.com/paper/2002.04027/) (2020)
- [DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation And Extraction](https://mlsanity.com/paper/2112.13520/) (2021)
- [Robust Speaker Extraction Network Based on Iterative Refined Adaptation](https://mlsanity.com/paper/2011.02102/) (2020)
- [Joint framework with deep feature distillation and adaptive focal loss for weakly supervised audio tagging and acoustic event detection](https://mlsanity.com/paper/2103.12388/) (2021)

## Built on by (most cited first, 1 of 1)

- [TripleC Learning and Lightweight Speech Enhancement for Multi-Condition Target Speech Extraction](https://mlsanity.com/paper/2512.04945/) (2025)

## Abstract (arXiv)

Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment mismatch between the test noisy speech and target speaker enrollment speech; 2) Hard sample mining and learning. In this paper, dynamic acoustic compensation (DAC) is proposed to alleviate the environment mismatch, by intercepting the noise or environmental acoustic segments from noisy speech and mixing it with the clean enrollment speech. To well exploit the hard samples in training data, we propose an adaptive focal training (AFT) strategy by assigning adaptive loss weights to hard and non-hard samples during training. A time-frequency multi-loss training is further introduced to improve and generalize our previous work sDPCCN for PSE. The effectiveness of proposed methods are examined on the DNS4 Challenge dataset. Results show that, the DAC brings large improvements in terms of multiple evaluation metrics, and AFT reduces the hard sample rate significantly and produces obvious MOS score improvement.