Probing Discrete Speech Tokens of Spoken Language Models

Sven Naber, Julia Koch, Pranav Singh, Alberto Saponaro, Ioanna Karagianni, Ngoc Thang Vu


Abstract
This paper presents a framework for systematic probing of discrete speech token representations in spoken language models (SLMs). We propose three complementary components: a distributional divergence analysis testing whether an attribute is reflected in token usage, token-based classifiers to quantify recoverability and an attribute-conditioned representation analysis revealing phonetic attribute realizations. As a demonstration we apply these probes to tokenizer outputs and model generations from CosyVoice2 and SparkTTS on LibriTTS-R and VCTK. We find that gender is encoded in their respective tokens but in different forms - the signal is more stable across stages and datasets in CosyVoice2, whereas SparkTTS shows weaker cross-stage consistency and stronger pause/prosody-related effects. Exploratory probes of valence, arousal, and dominance are weaker and less consistent. These results show that discrete speech tokens retain speaker-related information in different ways across architectures and that the proposed framework provides an interpretable basis for comparing token representations across spoken language modeling pipelines.
Anthology ID:
2026.lrec-1.184
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
2344–2354
Language:
External URL:
https://lrec.elra.info/lrec2026-main-184
DOI:
10.63317/4d4kttgdydde
Bibkey:
Cite (ACL):
Sven Naber, Julia Koch, Pranav Singh, Alberto Saponaro, Ioanna Karagianni, and Ngoc Thang Vu. 2026. Probing Discrete Speech Tokens of Spoken Language Models. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2344–2354, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Probing Discrete Speech Tokens of Spoken Language Models (Naber et al., LREC 2026)
Copy Citation: