Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends
Xingyu Shen, Runze Wang, Wei-Ping Zhu, Benoit Champagne
Abstract
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.
Create a lesson
Related papers
FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection
Chengxian Hu, Zhiming Ma, Mingjun Pan et al.
TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection
Huiyuan Liu, Zhiming Ma, Yanxing Liu et al.
Multi-Teacher Distillation for Cross-Domain Streaming Electrolaryngeal Speech Encoding
Benedikt Mayrhofer, Enrique Orozco Olivares, Franz Pernkopf et al.
Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification
Seungmin Seo, Oleg Aulov, P. Jonathon Phillips et al.
TTM-Bench: A Framework for Text-to-Music System Performance Benchmarking
Giorgia Adorni, Michela Papandrea, Battista Rimoldi et al.
VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval
Aaron Yee, Fengjie Lu, Jiarui Hai et al.