eess.AS · 2026-08-03 · No. 73
Audio and Speech Processing, 2026-08-03.
1 new papers in eess.AS. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens
Yi Luo, Rongzhi Gu, Jixun Yao
eess.AS · cs.AI · cs.LG · cs.SD
Balancing sequence length, representational capacity, and long-horizon stability is a central problem in autoregressive (AR) speech and audio generation. Representations with higher frame rates or greater capacity can preserve more signal detail, but they also make streaming generation more vulnerable to distribution drift and AR error accumulation. Conversely, shorter and more compressed representations simplify AR modeling, but their...
This edition is part of The Daily Abstract — eess.AS archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.