eess.AS · 2026-11-01 · No. 160
Audio and Speech Processing, 2026-11-01.
2 new papers in eess.AS. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
2 entries-
01
Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models
Anuj Diwan, David Harwath, Eunsol Choi
eess.AS · cs.CL · cs.LG · cs.SD
Voice-cloning TTS models synthesize an unseen speaker's voice from brief speech prompts, but it remains unclear which acoustic properties they represent and use. We introduce a feature-based interpretability framework for autoregressive voice-cloning TTS models, analyzing features from sparse autoencoders (SAEs), PCA, and random directions via sparse probing, steering, and quantitative auto-interpretability. We focus on Qwen3-TTS and extend...
-
02
The Importance of Speech Genre for End-of-Turn Detector Training
Rini Sharon, Kadri Hacioglu, Jeena Prakash, Andreas Stolcke
eess.AS · cs.AI
End-of-turn (EoT) detection has been studied mostly through features, models, and modalities, while the speech genre of the training data has drawn far less attention. We isolate this factor. Using one reproducible annotation pipeline, we build a matched pair of corpora, multi-turn human-human conversational and single-turn human-machine, and train the same streaming ConvLSTM EoT detector on each. Across four test sets the conversational...
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.