Hugging Face Trending Papers July 20, 2026

Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture

Read the original on Hugging Face Trending Papers →

Individuals with dysarthria face significant challenges in professional speaking scenarios such as conferences, presentations, and meetings, where real-time communication is crucial. While existing Augmentative and Alternative Communication (AAC) systems provide basic support, they often fail to meet the demands of professional speaking environments due to high latency and unnatural speech patterns.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jul 21

Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture

arXiv:2607. 17615v1 Announce Type: cross Abstract: Individuals with dysarthria face significant challenges in professional speaking scenarios such as conferences, presentations, and meetings, where real-time communication is crucial.

By Yuxuan Wu, Yifan Xu, Junkun Wang, Jiayong Jiang, Xin Zhao, Zhaojie Luo

llms multimodal

arXiv AI

Jun 18

Augmenting Dysarthric Speech Severity Assessment with MOS Supervision

arXiv:2606. 18645v1 Announce Type: cross Abstract: Dysarthria is a speech disorder marked by reduced intelligibility and communicative effectiveness.

By Kaimeng Jia, Minzhu Tu, Zengrui Jin, Siyin Wang, Chao Zhang

fine-tuning

arXiv AI

Jun 19

Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation

arXiv:2606. 19797v1 Announce Type: cross Abstract: Dysarthric speech recognition is crucial for facilitating effective communication among individuals with dysarthria.

By Paban Sapkota, Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Shrikanth Narayanan

fine-tuning multimodal

arXiv AI

Jun 18

Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech

arXiv:2603. 15988v3 Announce Type: replace-cross Abstract: Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies.

By Jaesung Bae, Xiuwen Zheng, Minje Kim, Chang D. Yoo, Mark Hasegawa-Johnson

fine-tuning multimodal benchmarks

OpenAI Blog

Oct 1, 2024

Introducing the Realtime API

Developers can now build fast speech-to-speech experiences into their applications

Hugging Face Trending Papers

Aug 11

myMediWhisper: Construction of Burmese Medical Speech Corpus and Whisper Fine-Tuning for Clinical Dialogue ASR

Although Whisper models benefit from large-scale multilingual pre-training, their performance on Burmese medical speech remains limited. This work presents a Burmese medical speech recognition framework built on a high-quality 28-hour corpus recorded and validated by native speakers.

fine-tuning multimodal benchmarks

Related stories

Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture

Augmenting Dysarthric Speech Severity Assessment with MOS Supervision

Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation

Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech

Introducing the Realtime API

myMediWhisper: Construction of Burmese Medical Speech Corpus and Whisper Fine-Tuning for Clinical Dialogue ASR