The paper introduces a sequence‑parallel band‑split enhancement front‑end called Parallel Time‑Band Mixer (PTBM) that removes recurrent unrolling within blocks. PTBM combines intra‑band temporal mixing with per‑frame cross‑band attention in a fully parallel architecture, while a learned Observation‑Adding (LOA) module suppresses ASR‑sensitive artifacts without development‑set tuning. Experiments on DNS Challenge and CHiME‑4 using frozen Whisper back‑ends show that this lightweight front‑end (0.96 M parameters, 0.58 GMAC/s) consistently lowers word error rate compared to recurrent band‑split baselines.
arXiv:2606. 12662v1 Announce Type: cross Abstract: Speech enhancement models typically apply uniform capacity across all frequencies, disregarding the non-uniform spectral resolution of human hearing.
arXiv:2604. 01832v1 Announce Type: cross Abstract: We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge.
arXiv:2604.06487v2 Announce Type: replace Abstract: Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR arch...
arXiv:2503. 00340v2 Announce Type: cross Abstract: Lightweight models are essential for real-time speech enhancement applications.
arXiv:2606. 14120v1 Announce Type: cross Abstract: Auditory attention decoding (AAD) aims to infer the attended speaker from neural responses in multi-speaker acoustic environments and is a key problem for neuro-steered hearing systems.
arXiv:2607. 17761v1 Announce Type: cross Abstract: Recently, speech deepfake detection (SDD) has achieved significant progress.
arXiv:2606. 13121v1 Announce Type: cross Abstract: Simultaneous speech-to-speech translation aims to enable near-real-time communication by minimizing latency, offering a compelling, real-time alternative to the high latency of consecutive translation.
arXiv:2601. 06199v3 Announce Type: replace-cross Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form speech is bottlenecked by the explosive growth of input tokens.
arXiv:2607. 20086v1 Announce Type: cross Abstract: State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks.
The paper presents a redesign of the LiSenNet speech‑enhancement model for deployment on the STM32N6570‑DK Neural‑ART microcontroller accelerator. By replacing the recurrent bottleneck with convolutional mixers, converting unsupported operations to static int8 primitives, and using bounded decoder activations, the authors achieve an NPU‑compatible model that matches or surpasses the original LiSenNet in quality (PESQ 3.08 vs 3.01 FP32) while running each 16 ms input hop in 4.83 ms (real‑time factor 0.30). The study demonstrates that co‑designing parameter count, operator compatibility, quantization range, and streaming state is essential for efficient real‑time speech enhancement on constrained NPUs.
arXiv:2606. 27320v1 Announce Type: cross Abstract: Neural audio autoencoders have become a core component of compression, feature extraction, and generation.
arXiv:2609.10366v1 Announce Type: cross Abstract: While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true...