cs.SD · 2026-08-12 · No. 82

Sound, 2026-08-12.

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

01 — The papers

3 entries
  1. 01

    Whisper-Aware LLM: Self-Supervised Uncertainty Learning for Robust Whispered Speech Recognition

    Gaopeng Xu, Zhenyu Wang, Zheng Xue, Yinfeng Xia, Haitao Yao

    cs.SD · cs.AI

    The signal ambiguity of whispered speech drives ASR systems toward two opposing failure modes: failing to capture whispered speech or hallucinatory transcription of noise. This paper introduces the Whisper-Aware LLM, a framework that teaches an Audio-LLM to perceive and react to this uncertainty. Our model develops an intrinsic self-awareness by learning to quantify the physical deficiencies of acoustic signals through targeted...

    arxiv.org/abs/2608.10836 · PDF

  2. 02

    DuplexWorld: Can voice agents help you get through the day?

    Aryan Vijay Bhosale, Harshit Rajgarhia, Akhil Pothanapalli, Asif Shaik, Abhishek Mukherji, Dinesh Manocha

    cs.SD · cs.AI · cs.CL

    Speech-to-speech (S2S) voice agents are increasingly being incorporated into enterprise for customer care and as daily companions for consumers owing to the ease of the conversational modality over text. However, existing benchmarks fail to holistically evaluate voice agents along axes that really matter and are shaped as tests of agentic tool calling against a database. We believe they fail to adequately account for the diversity of...

    arxiv.org/abs/2608.10716 · PDF

  3. 03

    Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Models

    Shuozhe Cheng, Kunlan Xiang, Mingxuan Li, Ji Zhang, Dongxiao Liu, Wenbo Jiang

    cs.SD · cs.AI

    Many studies have shown that specially crafted inputs can induce large language models (LLMs) to generate excessively long outputs, resulting in significant computational overhead and resource consumption. While most existing denial-of-service (DoS) attacks target text-only LLMs, end-to-end (E2E) speech LLMs are rapidly emerging. Existing text-based DoS attacks primarily rely on prompt engineering, such as adversarial suffixes or semantic...

    arxiv.org/abs/2608.10405 · 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.