arXiv:2603. 02794v2 Announce Type: replace-cross Abstract: We present TVF (Time-Varying Filtering), an interpretable, low-latency speech enhancement model for real-time, on-device assistive hearing.
arXiv:2606. 04103v1 Announce Type: cross Abstract: Conventional hearing aids rely on fixed, frequency-dependent amplification and compression to manage reduced sensitivity, which often fails to provide sufficient listening support in complex environments, such as situations with multiple speakers (the ``cocktail party'' problem).
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.
The paper investigates whether per‑frame early exit can improve compute‑matched performance for on‑device speech enhancement. By supervising every intermediate depth of a causal model and fine‑tuning output heads, the authors produce a family of static models that are more Pareto‑efficient than those trained from scratch, achieving up to 0.11 higher PESQ for equivalent compute and matching the best PESQ at 30% less compute. After int8 quantization, the dynamic enhancer performs on the same latency‑quality frontier as static models on an STM32N6 microcontroller, with the policy execution adding only 26 µs per frame and a 2.2% latency overhead from graph splitting.
arXiv:2609.36577v1 Announce Type: cross Abstract: Audio large language models (ALLMs) can reason about the content of audio recordings to perform complex tasks. However, these capabilities usually co...
arXiv:2607. 11801v1 Announce Type: cross Abstract: Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content.
arXiv:2607. 26472v1 Announce Type: cross Abstract: Audio deepfake detectors often degrade when generators, corpora, or recording conditions change.
arXiv:2606. 04210v1 Announce Type: cross Abstract: Randomized smoothing (RS) certifies robustness in the vector space where Gaussian noise is added.
The paper introduces RALCT, a lightweight Convolutional Transformer that combines randomized audio augmentations, MFCCs, and log‑mel spectrograms to extract robust features for environmental sound recognition. With only about 310,000 parameters, RALCT achieves state‑of‑the‑art accuracy—over 93% on UrbanSound8K, peaking at 94.56%—making it suitable for deployment on mobile devices. The authors also develop a mobile app that integrates the model to provide real‑time safety alerts for hearing‑impaired users.
arXiv:2609.21183v1 Announce Type: cross Abstract: Audio large language models (AudioLLMs) operate reactively, responding only when queried. We introduce proactive audio assistance, where an AudioLLM...
arXiv:2607. 00247v1 Announce Type: cross Abstract: Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors.
The paper introduces modality‑gated deep adapters, a parameter‑efficient method for adding new modalities to a frozen multimodal embedding language model without altering its existing outputs. These adapters are bottleneck modules attached to each decoder layer, grouped into modality‑specific packs that activate only during encoding of their own modality, ensuring exact preservation of the base model’s computation graph. Experiments on a 2B base model show significant gains in audio‑to‑text and thermal‑to‑text retrieval metrics, and the authors release the audio and thermal packs along with training and evaluation code.
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.