cs.SD · 2026-06-23 · No. 32

Sound, 2026-06-23.

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

    The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection

    Nicolas M. Müller, Pascal Debus

    cs.SD · cs.AI

    Provenance watermarking is increasingly treated as a safeguard for synthetic speech, whether built directly into speech-generation models such as Chatterbox, provided through dedicated techniques such as AudioSeal, or deployed by commercial platforms such as ElevenLabs. We identify a previously uncharacterized liability: when synthetic speech is watermarked and human speech is not, detectors trained alongside latch onto the watermark as a...

    arxiv.org/abs/2606.23335 · PDF

  2. 02

    From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection

    Jan Jasiński, Mateusz Barański, Julitta Bartolewska, Marcin Witkowski, Konrad Kowalczyk

    cs.SD · cs.AI · eess.AS

    Hallucinations of ASR models - fluent transcriptions with no basis in audio - degrade system performance and pose risks in downstream applications. Robust detection of such errors remains a challenge. This paper studies Whisper large v3 hallucination detection on real-speech human-annotated data across three paradigms: text-based, LLM-based, and internal decoder state probing. Text classifiers utilizing metrics for text evaluation achieve...

    arxiv.org/abs/2606.23060 · PDF

  3. 03

    HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems

    Mateusz Barański, Jan Jasiński, Julitta Bartolewska, Marcin Witkowski, Konrad Kowalczyk

    cs.SD · cs.AI · eess.AS

    End-to-end Automatic Speech Recognition (ASR) systems hallucinate on natural speech, yet existing mitigation methods are typically evaluated on non-speech or artificially corrupted audio. We introduce HALAS, the first human-annotated dataset of naturally occurring hallucinations from seven state-of-the-art ASR models on real unprocessed earnings call recordings. HALAS provides span-level labels, enabling analysis of hallucination patterns and...

    arxiv.org/abs/2606.23048 · 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.