Portrait de Eeshan Gunesh Dhekane n'est pas disponible

Eeshan Gunesh Dhekane

Alumni

Publications

Scaling Properties of Continuous Diffusion Spoken Language Models
Jason Ramapuram
Eeshan Gunesh Dhekane
Amitis Shidani
Dan Busbridge
Bogdan Mazoure
Zijin Gu
Russ Webb
Tatiana Likhomanenko
Navdeep Jaitly
Speech-only spoken language models (SLMs) lag behind text and text-speech models in performance, with recent discrete autoregressive (AR) SL… (voir plus)Ms indicating significant computational and data demands to match text models. Since discretizing continuous speech for AR creates bottlenecks, we explore whether continuous diffusion (CD) SLM is more viable. To quantify the SLMs linguistic quality, we introduce the phoneme Jensen-Shannon divergence (pJSD) metric. Our analysis reveals CD SLMs, mirroring AR behavior, exhibit scaling laws for validation loss and pJSD, and show optimal token-to-parameter ratios decreasing as compute scales. However, for the latter, loss becomes insensitive to choice of data and model sizes, showing potential for fast inference. Scaling CD SLMs to 16B parameters with tens of millions of hours of conversational data enables generation of emotive, prosodic, multi-speaker, multilingual speech, though achieving long-form coherence remains a significant challenge.
2026-04-26
arXiv (prépublication)
doi.org
arxiv.org
Poly-View Contrastive Learning
Amitis Shidani
R Devon Hjelm
Jason Ramapuram
Russell Webb
Eeshan Gunesh Dhekane
Dan Busbridge
2024-01-15
ICLR.cc/2024/Conference (poster)
openreview.net
openreview.net