cs.SD · 2026-09-28 · No. 127

Sound, 2026-09-28.

5 new papers in cs.SD. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

5 entries
  1. 01

    AFA-Net: A Differential Attention Approach for Auditory Attention Detection

    Philip H. Lee, Shreeram Suresh Chandra, Karan Thakkar, John H. L. Hansen

    cs.SD · cs.LG · eess.SP

    Auditory Attention Detection (AAD) utilizes electroencephalographic (EEG) signals to identify a target speaker in a multi-speaker environment. Despite considerable progress, existing deep learning architectures often lack explicit mechanisms for handling noisy EEG data. To address this limitation, we propose Auditory Focus Attention Networks (AFA-Net), a machine learning framework that replaces vanilla attention with a simple yet flexible...

    arxiv.org/abs/2609.31402 · PDF

  2. 02

    Acoustic-to-Text KV Compression for Full-Duplex Speech Models

    Yejin Lee, Seungbeom Kim, Yongha Lee, Kyuhong Shim

    cs.SD · cs.AI · eess.AS

    Full-duplex speech language models continuously accumulate acoustic key-value (KV) states, making long-running interactions memory-intensive. During listening, the model can finish processing an audio unit before the next arrives; we term the remaining interval listening-time slack. We propose acoustic-to-text KV compression, which introduces a transcription side channel to convert incoming speech into compact textual memory within this...

    arxiv.org/abs/2609.31224 · PDF

  3. 03

    BAT-CLIP: Trimodal Alignment of Brain, Audio and Text

    Suhyun Kim, Jinmo Han, Danny Dongyeop Han, Ahhyun Lucy Lee, Jewoon Lee, Yonghyeon Gwon, Zach Paris, Chun Kee Chung,...

    cs.SD · cs.AI · cs.LG · eess.AS

    Decoding and interpreting naturalistic speech from the brain increasingly relies on alignment to pretrained speech and language representation spaces. However, current CLIP-style brain-speech alignment ground neural activity to a single anchor modality-audio or text-despite the brain's inherently multimodal speech processing. This induces a trade-off: audio anchoring preserves temporal structure but weakens linguistic separability, while text...

    arxiv.org/abs/2609.31180 · PDF

  4. 04

    BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio

    Sania Fatima Sayed, John W. Holloway, Reyer Zwiggelaar, Faisal I. Rezwan

    cs.SD · cs.LG · eess.AS

    Speech-breath segmentation is a fundamental preprocessing step in respiratory audio analysis, enabling applications such as respiratory acoustic biomarker extraction, lung function prediction and disease monitoring. Existing approaches, including threshold methods, Fourier Transform-based techniques, and unsupervised and pretrained voice activity detection (VAD) models, primarily focus on speech detection and often classify breathing events...

    arxiv.org/abs/2609.31165 · PDF

  5. 05

    Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search

    Ben Hayes, Haokun Tian, Stefan Lattner

    cs.SD · cs.LG · eess.AS

    Sound matching can be formulated as optimizing synthesizer parameters against an audio-domain objective. However, objectives derived from generic audio representations are often difficult to optimize, while direct search requires rendering every candidate. We introduce Synth-JEPA, which learns mutually predictive audio and parameter representations from paired synthesizer data. At inference, candidate parameters are scored directly in this...

    arxiv.org/abs/2609.31024 · PDF

This edition is part of The Daily Abstract — cs.SD archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.