# Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends

arXiv: https://arxiv.org/abs/2608.30326 · HTML: https://mlsanity.com/paper/2608.30326/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR](https://mlsanity.com/paper/2201.06685/) (2022)
- [High Fidelity Speech Enhancement with Band-split RNN](https://mlsanity.com/paper/2212.00406/) (2022)
- [The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement](https://mlsanity.com/paper/2406.03460/) (2024)
- [Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition](https://mlsanity.com/paper/2203.14838/) (2022)
- [Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network](https://mlsanity.com/paper/2406.18928/) (2024)
- [Time-Domain Speech Enhancement for Robust Automatic Speech Recognition](https://mlsanity.com/paper/2210.13318/) (2022)
- [A light-weight full-band speech enhancement model](https://mlsanity.com/paper/2206.14524/) (2022)
- [SuPseudo: A Pseudo-supervised Learning Method for Neural Speech Enhancement in Far-field Speech Recognition](https://mlsanity.com/paper/2505.24450/) (2025)
- [Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning](https://mlsanity.com/paper/2509.21833/) (2025)

## Abstract (arXiv)

Speech enhancement is often used as a front-end for robust ASR, yet recurrent temporal and cross-band modules introduce sequential dependencies that reduce parallel efficiency. In this paper, we present a sequence-parallel band-split enhancement front-end built on a Parallel Time-Band Mixer (PTBM) block that eliminates within-block recurrent unrolling. PTBM integrates intra-band temporal mixing and per-frame cross-band attention within a unified parallel architecture, enabling efficient contextual modeling across both time and frequency dimensions. The system retains the mask-plus-residual reconstruction interface and introduces learned Observation-Adding (LOA) to suppress ASR-sensitive artifacts without development-set tuning. Experiments on DNS Challenge and CHiME-4 with frozen Whisper back-ends show that the proposed front-end consistently reduces word error rate relative to recurrent band-split baselines while requiring only 0.96 M parameters and 0.58 GMAC/s for the front-end network.