cs.SD · 2026-10-06 · No. 135

Sound, 2026-10-06.

3 new papers in cs.SD. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

3 entries
  1. 01

    Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model

    Sahil Mahendrakar

    cs.SD · cs.AI · cs.CL · cs.LG · eess.AS

    We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is trained separately against the frozen teacher. It has 10x fewer parameters and needs 15x less compute. We first synthesize a corpus with the teacher and keep its durations, pitch, energy and phoneme features....

    arxiv.org/abs/2610.06817 · PDF

  2. 02

    Revisiting Label-Free Speaker Embedding Enhancement with vMF Profile Likelihood

    Seunghwan Kim, Jinyong Kim, Sooyoung Yang, Youngjin Ko, Myungjoo Kang

    cs.SD · cs.LG

    Embedding enhancement improves speaker verification under acoustic mismatch without modifying a frozen backbone. Recent work has established a practical label-free setting for this task, but often adopts increasingly structured formulations. Here, the clean target is directly observed during training, making enhancement a matching problem on the unit hypersphere. We model the clean target with a von Mises--Fisher (vMF) likelihood and profile...

    arxiv.org/abs/2610.06691 · PDF

  3. 03

    Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants

    Aadam Haq, Oggi Rudovic, Malcolm Chadwick, Jay Rainey, Shucong Zhang, Ricardo Guerrero, Sourav Bhattacharya, Maja Pantic

    cs.SD · cs.AI · cs.CL

    AI voice assistants often use Automatic Speech Recognition (ASR) with LLM-based reasoning, yet existing systems struggle with regional British accents, including Scottish, Irish, and Welsh accents, since most ASR models are trained predominantly on American English voice data. Consequently, errors can carry through to the LLM stage, corrupting tool-call arguments and producing wrong or missing responses, which is especially costly in finance....

    arxiv.org/abs/2610.06587 · PDF

This edition is part of The Daily Abstract — cs.SD archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.