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

Shree Harsha Bokkahalli Satish, Harm Lameris, Olivier Perrotin, Gustav Eje Henter, Eva Szekely


Abstract
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 direct setting for probing biases in speech foundation models than dialogue does. In this work we present the first systematic evaluation of bias in SC, investigating how gender and phonation type (breathy, creaky, end-creak) affect continuation behaviour. We evaluate three recent models: SpiritLM (base and expressive), VAE-GSLM, and SpeechGPT across speaker similarity, voice quality preservation, and text-based bias metrics. Results show that while both speaker similarity and coherence remain a challenge, textual evaluations reveal significant model and gender interactions: once coherence is sufficiently high (for VAE-GSLM), gender effects emerge on text-metrics such as agency and sentence polarity. In addition, continuations revert toward modal phonation more strongly for female prompts than for male ones, revealing a systematic voice-quality bias. These findings highlight SC as a controlled probe of socially relevant representational biases in speech foundation models, and suggest that it will become an increasingly informative diagnostic as continuation quality improves.
Anthology ID:
2026.iaai-1.2
Volume:
Proceedings of the Second Workshop of Identity Aware AI
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
A Pranav, Valerio Basile, Neele Falk, David Jurgens, Gabriella Lapesa, Anne Lauscher, Soda Marem Lo
Venues:
iaai | WS
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
12–19
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-iaai-02
DOI:
10.63317/3h9cs6yh6gvq
Bibkey:
Cite (ACL):
Shree Harsha Bokkahalli Satish, Harm Lameris, Olivier Perrotin, Gustav Eje Henter, and Eva Szekely. 2026. Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias. In Proceedings of the Second Workshop of Identity Aware AI, pages 12–19, Palma de Mallorca, Spain. European Language Resources Association.
Cite (Informal):
Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias (Bokkahalli Satish et al., iaai 2026)
Copy Citation: