arXiv:2609.38658v1 Announce Type: cross
Abstract: TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but the...
By Jian Chen, You Zhang, Mark Vinton
VietMed is a Vietnamese medical speech recognition dataset featuring 16 h of labeled medical speech, 1 000 h of unlabeled medical speech, and 1 200 h of unlabeled general‑domain speech. It claims to be the largest public medical ASR dataset worldwide in seven dimensions—total duration, speaker count, disease coverage, recording conditions, speaker roles, unique medical terms, and accents—and also the largest Vietnamese speech dataset by duration. The authors release pre‑trained models (w2v2‑Viet and XLSR‑53‑Viet) and fine‑tuned medical ASR models, showing that XLSR‑53‑Viet outperforms the state‑of‑the‑art XLSR‑53 by reducing WER from 51.8 % to 29.6 % on a medical test set.
whyItMatters":"The dataset and models provide the first large‑scale, publicly available Vietnamese medical ASR resource, enabling research and development of medical speech technologies in a language and domain that previously lacked sufficient data."
By Khai Le-Duc
Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.
The paper introduces a trilingual spoken hallucination detection benchmark covering English, Russian, and Kazakh news, with 12,013 samples that include synthetic alterations and severity levels, as well as 290 fact‑checked misinformation items. Detectors are evaluated in a reference‑free setting on text, ASR transcripts, and audio, revealing that most models underperform baseline classifiers, except Gemma‑3n on transcripts. Synthetic‑trained detectors achieve high macro‑F1 scores on real‑world misinformation, but Russian provenance analysis highlights model‑dependent signals that confound synthetic benchmarks.
By Meruyert Aristombayeva, Jason S. Lucas, Chaewan Chun, Dongwon Lee
Speaker recognition has advanced rapidly with large-scale training datasets, yet Vietnamese remains under-resourced, with existing corpora limited in scale and acoustic diversity. Most large-scale datasets rely on facial cues to link speech with speaker identities, restricting data collection to recordings where speakers appear on camera.
Audio large language models (Audio LLMs) often fail to transcribe English‑Mandarin code‑switching speech, exhibiting language omission, translation‑instead‑of‑transcription, and hallucination. By applying Direct Preference Optimization (DPO) with 100 K preference pairs, the models learn to preserve mixed‑language content rather than translate, leading to significant reductions in mixed‑error rates (up to 89.6% in‑distribution). The study demonstrates that DPO can effectively align multilingual Audio LLMs for accurate code‑switching transcription.
By Trung Nguyen Quang, Cheng Yi Lewis Won, Minh Duc Pham, Yingxu He, Shuo Sun, Ai Ti Aw