The paper introduces the first open Speech Language Model for Basque, built on the LLaMA‑Omni architecture and a Latxa backbone, aimed at low‑latency, end‑to‑end spoken interaction. To overcome data scarcity, the authors translated the English VoiceAssistant‑400K corpus into Basque and synthesized audio with a Basque TTS system. Evaluation shows the model achieves a content quality score of 3.86/5, a 9.94% word error rate for intelligibility, and a 3.07 UTMOS for audio quality, demonstrating the feasibility of advanced spoken interaction in a low‑resource language.
arXiv:2609.36920v1 Announce Type: new Abstract: Comprehensive evaluations of automatic speech recognition (ASR) for Iberian languages remain limited, and low-resource languages, biases, and efficienc...
The study fine‑tunes the Whisper Small model for Automatic Speech Recognition (ASR) in Baniwa, an indigenous Arawakan language. Using a 0.54‑hour corpus of 1,373 manually transcribed recordings, the fine‑tuned model achieved a Word Error Rate of 37.5% and a Character Error Rate of 7.45%. These results provide an initial baseline for Baniwa ASR and suggest that multilingual foundation models can be adapted to extremely low‑resource languages.
arXiv:2608. 19361v1 Announce Type: new Abstract: This study reports the development of an Automatic Speech Recognition (ASR) system in Mizo, a low-resource language.
arXiv:2508. 05149v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks.
Nord-Parl-TTS is an open text‑to‑speech dataset for Finnish and Swedish created from recordings of Nordic parliamentary proceedings. It contains 900 hours of Finnish and 5 090 hours of Swedish speech, processed with an adapted Emilia pipeline and accompanied by unified evaluation sets for model development and benchmarking. The dataset aims to reduce the resource gap in TTS between high‑ and lower‑resourced 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.
arXiv:2609.10022v1 Announce Type: cross Abstract: Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, la...
arXiv:2609.09554v1 Announce Type: new Abstract: We introduce BuzzASR, a collection of language-specialized fine-tuned Whisper models adapted for automatic speech recognition (ASR) in 102 languages. L...
arXiv:2603.23938v2 Announce Type: replace Abstract: Most testbeds for omni-modal models assess multimodal understanding via textual outputs, leaving it unclear whether these models can properly speak...
arXiv:2609.23825v1 Announce Type: new Abstract: We present a comprehensive benchmark of Federated Learning (FL) for multilingual Automatic Speech Recognition (ASR), evaluating four Speech-LLM archite...
The paper introduces phoneme‑guided initialization for large language model‑based speech recognition. By pre‑training an audio encoder on speech‑to‑phoneme conversion and an LLM on phoneme‑to‑grapheme conversion, then fine‑tuning jointly on ASR, the method leverages phoneme‑mediated processing within an end‑to‑end framework. Experiments on Japanese, Chinese, Tatar, and Urdu demonstrate that this approach matches or surpasses both cascaded S2P‑P2G baselines and end‑to‑end models without phoneme initialization.
Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, lacking the curated corpora behind state-of-the-art s...