paper-with-me

홈 › Papers

Lost in Phonation: Voice Quality Variation as an Evaluation Dimension for Speech Foundation Models

2025-10-29 · Harm Lameris, Shree Harsha Bokkahalli Satish, Joakim Gustafson, Éva Székely arxiv

Recent advances in Speech Foundation Models (SFMs) enable direct processing of raw audio, allowing models to respond to subtle paralinguistic variation. However, how these models interpret non-lexical cues remains largely unstudied. We introduce VQ-Bench, a controlled evaluation suite featuring a parallel dataset of synthesized modal, breathy, creaky, and end-creak phonation types. We evaluate SFM sensitivity through open-ended generation across four ecologically valid domains, alongside speech emotion recognition. Our results reveal performance gaps: while a leading commercial API failed basic biometric sanity checks, other models exhibited systematic shifts in agency, empathy, and leadership based on phonation. Our findings also highlight gender asymmetries in salary and leadership endorsements, demonstrating that SFMs may mirror or amplify human social biases. This work establishes a reproducible framework for ensuring responsible paralinguistic interpretation in speech-based AI.

📄 PDF Abstract BibTeX arXiv:2510.25577

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Emotion RecognitionQuestion Answering

Similar Papers 제목 키워드 기반

Towards detecting the pathological subharmonic voicing with fully convolutional neural networks

2025-01-15 · Takeshi Ikuma, Melda Kunduk, Brad Story, Andrew J. McWhorter

Many voice disorders induce subharmonic phonation, but voice signal analysis is currently lacking a technique to detect the presence of subharmonics reliably. Distinguishing subharmonic phonation from normal phonation is…

A Database of Laryngeal High-Speed Videos with Simultaneous High-Quality Audio Recordings of Pathological and Non-Pathological Voices

2016-05-01 · LREC 2016 5 · Philipp Aichinger, Immer Roesner, Matthias Leonhard, Doris-Maria Denk-Linnert 외

Auditory voice quality judgements are used intensively for the clinical assessment of pathological voice. Voice quality concepts are fuzzily defined and poorly standardized however, which hinders scientific and clinical …

Vocal Bursts Intensity Prediction

Voice Pathology Detection Using Phonation

2025-08-11 · Sri Raksha Siva, Nived Suthahar, Prakash Boominathan, Uma Ranjan arxiv

Voice disorders significantly affect communication and quality of life, requiring an early and accurate diagnosis. Traditional methods like laryngoscopy are invasive, subjective, and often inaccessible. This research pro…

Voice pathology detectionData Augmentation

Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias

2025-09-26 · Shree Harsha Bokkahalli Satish, Harm Lameris, Olivier Perrotin, Gustav Eje Henter 외 arxiv

Speech Continuation (SC) is the task of generating a coherent extension of a spoken prompt while preserving both semantic context and speaker identity. Because SC is constrained to a single audio stream, it offers a more…

Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment

2026-04-21 · Huanchen Cai, Sten Ternström arxiv

This study investigates voice mapping as an evaluation framework for text-to-speech (TTS) synthesis quality. The study analyzes six TTS models, including historical and recent ones. The metrics are crest factor, spectrum…