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.
By Cl\'ement Laroche, Rasmus Kongsgaard Olsson
NAVIR is an end‑to‑end audio‑visual speech recognition system designed for the BrainChip Akida neuromorphic processor, which only supports sequential 2‑D convolutions. The architecture separates spatial and temporal encoding into three AkidaNet modules—per‑frame visual, temporal video, and spectrogram audio encoders—fused by a lightweight predictor and decoded with constrained beam search. Trained with CTC on noise‑augmented audio and fine‑tuned via quantization‑aware training, the quantized model achieves 14.0% WER on GRID’s unseen‑speaker split and 3.3% on overlapped‑speaker split, outperforming audio‑only baselines, and delivers 98.6% command accuracy at 1.5% WER on an industrial‑command corpus, while offering a 13‑fold energy advantage over conventional ANNs and roughly 5‑fold lower energy per inference than a Raspberry Pi CPU.
By Leonidas Delimpasis, Panagiota Moraiti, Antonis Porichis, Panos Chatzakos, Michail Karamousadakis
arXiv:2606. 06837v1 Announce Type: cross Abstract: Scripted vs spontaneous speech detection is appealing for interview guardrails, but benchmark performance can be inflated by shortcuts tied to corpus identity, channel conditions, and recording artifacts rather than speaking style itself.
By Vsevolod (V.), Kovalev, Pranay Manocha
arXiv:2509. 00078v2 Announce Type: replace-cross Abstract: The emergence of large language models (LLMs) has transformed spoken dialog systems, yet the optimal architecture for real-time on-device voice agents remains an open question.
By Tatiana Likhomanenko, Richard He Bai, Zijin Gu, Zakaria Aldeneh, Shiladitya Dutta, Luke Carlson, Han Tran, Yizhe Zhang, Ruixiang Zhang, Huangjie Zheng, Navdeep Jaitly
arXiv:2610.07046v1 Announce Type: cross
Abstract: Visual speech promises noise-robust keyword spotting, yet a visual stream is not necessarily used. On a tri-modal query-by-example keyword spotting (...
By Ming-Hsiang Hu, Kuan-Tang Huang, Hung-Shin Lee, Berlin Chen
arXiv:2606. 18122v1 Announce Type: cross Abstract: Embedded machine learning moves inference from cloud services to resource-constrained devices that must acquire data, preprocess signals, run a model, and act within tight limits on memory, energy, and latency.
By Mostafa Darvishi
arXiv:2510. 12947v3 Announce Type: replace-cross Abstract: Voice activity detection (VAD) serves as an early gate in voice-assistant pipelines for smart devices.
By Hamed Jafarzadeh Asl, Amin Edraki, Mahsa Ghazvini Nejad, Masoud Asgharian, Mohammadreza Sadeghi, Yuanhao Yu, Vahid Partovi Nia
arXiv:2606. 01483v1 Announce Type: cross Abstract: Long-form automatic speech recognition (ASR) requires both high accuracy and low latency, but existing systems force a trade-off between the two.
By Wei-Tzu Lee, Keisuke Kamahori, Baris Kasikci
arXiv:2310.11379v2 Announce Type: replace-cross
Abstract: Voice-based interfaces rely on a wake-up word mechanism to initiate communication with devices. However, achieving a robust, energy-efficient...
By Fernando L\'opez, Jordi Luque, Carlos Segura, Pablo G\'omez
PromptKWS is a new prompt‑guided keyword spotting framework that enhances open‑vocabulary KWS accuracy. It introduces the Prompt Phrases Prediction Network (PPN), an encoder‑decoder that extracts keyword prompt embeddings, which are then integrated into the KWS encoder via a Prompt‑acoustic Multi‑head Cross‑attention module. Experiments show that PromptKWS raises the wake‑up rate by more than 10% and improves overall accuracy by over 15% in noisy, pronunciation‑variant real‑world settings.
By Gaopeng Xu, Chengfei Li, Xianliang Wang, Lin Zhu, Juan Wei, Wenpeng Li, Jianwei Niu, Jie Gao
arXiv:2606. 11279v1 Announce Type: cross Abstract: Automatic speech recognition systems have been shown to under-perform when it comes to transcribing words rarely seen in the training data, namely specialized terminology.
By Leonor Barreiros, Raul Monteiro, Afonso Mendes, Gon\c{c}alo M. Correia
arXiv:2503. 00340v2 Announce Type: cross Abstract: Lightweight models are essential for real-time speech enhancement applications.
By Xiaobin Rong, Leyan Yang, Dahan Wang, Yuxiang Hu, Changbao Zhu, Kai Chen, Jing Lu