arXiv AI June 8, 2026 By Naman Kothari, Arjun Gangwar, Adarsh Arigala, S Umesh

Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations

arXiv:2606. 06740v1 Announce Type: cross Abstract: Discrete speech units obtained via k-means clustering of self supervised embeddings entangle phonetic, speaker, and language information, causing speaker mixing and cross-lingual interference in multilingual multi-speaker speech generation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 26

Neural Speaker Diarization via Multilingual Training: Evaluation on Low-Resource Nepali-Hindi Speech

arXiv:2606. 26144v1 Announce Type: cross Abstract: Speaker diarization, the task of determining "who spoke when" in a multi-speaker recording, is a critical component in applications such as meeting transcription, accessibility tools, and multilingual information retrieval.

By Samip Neupane, Sandesh Pokhrel, Sandesh Pyakurel, Basanta Joshi

safety

arXiv AI

Jul 28

Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages

arXiv:2607. 23808v1 Announce Type: cross Abstract: In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India.

By Deovrat Mehendale, Aditya Mehndiratta, Dhruv Rathi, Kaushal Bhogale, Mitesh M. Khapra

llms multimodal benchmarks

arXiv Machine Learning

Jul 14

An Empirical Recipe for Universal Phone Recognition

arXiv:2603. 29042v2 Announce Type: replace-cross Abstract: Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive.

By Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi, Eunjung Yeo, William Chen, Shinji Watanabe, David R. Mortensen

benchmarks

arXiv AI

Jun 17

L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification

arXiv:2606. 17416v1 Announce Type: cross Abstract: Multilingual speaker verification remains challenging because language-dependent acoustic variability causes speaker identity to become entangled with linguistic characteristics, degrading generalization across languages.

By Hyung-Seok Oh, Deok-Hyeon Cho, Seung-Bin Kim, Seong-Whan Lee

rag fine-tuning benchmarks

arXiv Machine Learning

Jun 30

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings

arXiv:2509. 15001v3 Announce Type: replace-cross Abstract: Child-centered daylong recordings are essential for studying early language development, but existing speech models trained on clean adult data perform poorly due to acoustic and linguistic differences.

By Th\'eo Charlot, Tarek Kunze, Maxime Poli, Alejandrina Cristia, Emmanuel Dupoux, Marvin Lavechin

arXiv Machine Learning

Jun 16

Scaling Human and G2P Supervision for Robust Phonetic Transcription

arXiv:2606. 16019v1 Announce Type: cross Abstract: Expert phonetic annotation is costly, especially for non-standard dialects and atypical speech.

By Alexander Metzger, Aruna Srivastava, Ruslan Mukhamedvaleev

multimodal benchmarks

Related stories

Neural Speaker Diarization via Multilingual Training: Evaluation on Low-Resource Nepali-Hindi Speech

Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages

An Empirical Recipe for Universal Phone Recognition

L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings

Scaling Human and G2P Supervision for Robust Phonetic Transcription