2022/10/13 by Guan-Ting Lin, Chi-Luen Feng, Lin, Guan-Ting +16 · 9 citations
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Natural Language Processing Techniques #Speech Recognition and Synthesis #Speech and dialogue systems #cs.CL #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2210.07185
Accepted to IEEE SLT 2022
openalex publication_date 2022/10/13 · arxiv created 2022/10/26 · arxiv updated 2022/10/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Self-Supervised Learning (SSL) from speech data has produced models that have achieved remarkable performance in many tasks, and that are known to implicitly represent many aspects of information latently present in speech signals. However, relatively little is known about the suitability of such models for prosody-related tasks or the extent to which they encode prosodic information. We present a new evaluation framework, SUPERB-prosody, consisting of three prosody-related downstream tasks and two pseudo tasks. We find that 13 of the 15 SSL models outperformed the baseline on all the prosody-related tasks. We also show good performance on two pseudo tasks: prosody reconstruction and future prosody prediction. We further analyze the layerwise contributions of the SSL models. Overall we conclude that SSL speech models are highly effective for prosody-related tasks.