eess.AS · 2026-06-25 · No. 34

Audio and Speech Processing, 2026-06-25.

4 new papers in eess.AS. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

4 entries
  1. 01

    SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios

    Jinming Zhang, Wei Rao, Xionghu Zhong, Eng Siong Chng

    eess.AS · cs.AI

    Conventional audio pipelines typically treat speech enhancement (SE) and automatic gain control (AGC) as discrete modules, which often limits overall performance. For instance, applying AGC before SE may inadvertently amplify background noise, while prioritizing SE tends to over-suppress low-volume speech. To address these limitations, we propose SE-AGCNet, an end-to-end framework that jointly optimizes SE and AGC. Tailored for meeting...

    arxiv.org/abs/2606.25959 · PDF

  2. 02

    Adaptive Oscillatory Inductive Bias for Modeling Sharp Prosodic Dynamics in Diffusion-Based TTS

    Sandipan Dhar, Nirmesh J. Shah, Ashishkumar P. Gudmalwar, Pankaj Wasnik

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

    Diffusion-based text-to-speech (TTS) models have achieved significant improvements in speech quality. However, modeling sharp prosodic transitions and rapid pitch variations in expressive speech remains challenging. Existing diffusion-based TTS decoders commonly utilize periodic nonlinearities such as Snake activation function to capture harmonic structures, but this activation funcation provides limited adaptability when modeling abrupt...

    arxiv.org/abs/2606.25424 · PDF

  3. 03

    CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations

    Ram Annamdevula, Ankit Tatawat, Ashishkumar P. Gudmalwar, Nirmesh J. Shah, Pankaj Wasnik

    eess.AS · cs.AI · cs.SD

    Accent conversion and controllability remain fundamental challenges in cross-lingual text-to-speech (TTS), particularly for low-resource and phonetically diverse Indic languages. While recent large language model (LLM)-based TTS systems exhibit strong cross-lingual generalization, they provide limited explicit control over accent characteristics and intensity. In this paper, we propose CrossAccentTTS, a framework that enables both accent...

    arxiv.org/abs/2606.25403 · PDF

  4. 04

    Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable Assistant

    Milosz Dudek, Daria Hemmerling, Kamil Kwarciak, Maciej Stroinski, Maria Pensko, Mateusz Kowalewski, Leonid...

    eess.AS · cs.AI · cs.MA

    Early identification of speech sound errors in children is often limited by access to specialists, motivating lightweight screening tools that can operate outside the clinic. We present a screening pipeline for Polish-speaking children focused on sibilant substitutions, coupling a wav2vec2-based CTC token recognizer with alignment-based error typing and a template-grounded caregiver assistant for screening, not diagnosis. On a held-out test...

    arxiv.org/abs/2606.25181 · PDF

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.

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.