mlsanityData to 14 Oct 2026

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

arXiv 2608.30326 ↗First posted 31 Aug 2026cs.SD cs.AIcited by 0

Not on the map. Why?

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.

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

17 of 20 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  5. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 406
  6. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 340
  7. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 216
  8. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 133
  9. 2022How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASRcited by 28
  10. 2022High Fidelity Speech Enhancement with Band-split RNNcited by 16
  11. 2024The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancementcited by 12
  12. 2022Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognitioncited by 10
5 more
  1. 2024Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Networkcited by 4
  2. 2022Time-Domain Speech Enhancement for Robust Automatic Speech Recognitioncited by 2
  3. 2022A light-weight full-band speech enhancement modelcited by 1
  4. 2025SuPseudo: A Pseudo-supervised Learning Method for Neural Speech Enhancement in Far-field Speech Recognitioncited by 1
  5. 2025Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruningcited by 1

Built on by

Not cited yet.