10 papers
A Temporal-Envelope Frontend with Learnable Per-Channel Energy Normalization for Whisper-Based Children's ASR
Edem Ahadzi, Ruchi Pandey, Tomi H. Kinnunen
Temporal envelopes carry cues critical to speech intelligibility, yet ASR frontends based on log-mel spectrograms do not explicitly model continuous sub-band envelope structure. Th…
How Bilingual Are SSL Speech Models? Cross-Lingual Probing of Articulatory Encoding with Finnish and Russian EMA
Ailín Pollio San Pedro, Tomi Kinnunen, Alexandre Nikolaev +1
SSL speech models capture rich phonetic, prosodic, and acoustic patterns from raw audio, yet how they encode articulatory information across diverse languages remains unclear. Usin…
Beyond Speaker Independence: Evaluating Cross-Lingual Acoustic-to-Articulatory Inversion Across Finnish and Russian
Ruchi Pandey, Tomi Kinnunen
Acoustic-to-articulatory inversion (AAI) remains challenging under domain shifts where changes in speaker attributes and cross-language conditions often degrade performance. We con…
Phonetically Explainable Speech Deepfake Detection
Manasi Chhibber, Jagabandhu Mishra, Tomi H. Kinnunen
Speech deepfake detection is predominantly treated as an opaque classification task where all temporal frames are aggregated equally. This ignores that different phonetic categorie…
Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning
Xi Xuan, Wenxin Zhang, Zhiyu Li +3
Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator, often assuming that the resulting so…
Cyclostationarity Analysis as a Complement to Self-Supervised Representations for Speech Deepfake Detection
Cemal Hanilçi, Md Sahidullah, Tomi Kinnunen
Speech deepfake detection (SDD) is essential for maintaining trust in voice-driven technologies and digital media. Although recent SDD systems increasingly rely on SSL representati…