HuPER is a human-inspired framework that models phonetic perception as adaptive inference over acoustic‑phonetics evidence and linguistic knowledge. Using only 100 hours of training data, it achieves state‑of‑the‑art phonetic error rates on five English benchmarks and demonstrates strong zero‑shot transfer to 95 unseen languages. It uniquely enables adaptive, multi‑path phonetic perception across diverse acoustic conditions, and all training data, models, and code are open‑sourced.
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.
arXiv:2604. 14606v2 Announce Type: cross Abstract: Universal speech enhancement (USE) aims to restore speech signals from diverse distortions across multiple sampling rates.
arXiv:2607. 02633v1 Announce Type: new Abstract: We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language modeling.
arXiv:2606. 07030v1 Announce Type: cross Abstract: We analyse error patterns of raw waveform acoustic models on TIMIT phone recognition beyond the overall phone error rate (PER).
arXiv:2607. 09020v1 Announce Type: cross Abstract: Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately.
arXiv:2607. 01965v1 Announce Type: cross Abstract: Neural TTS systems can sound natural across languages, but naturalness does not guarantee the preservation of sound contrasts that distinguish words from their grammatical forms.
arXiv:2606. 16019v1 Announce Type: cross Abstract: Expert phonetic annotation is costly, especially for non-standard dialects and atypical speech.
Neural TTS systems can sound natural across languages, but naturalness does not guarantee the preservation of sound contrasts that distinguish words from their grammatical forms. Standard metrics like MOS do not test for this.
arXiv:2606. 20518v1 Announce Type: new Abstract: Flow-matching text-to-speech systems achieve remarkable zero-shot quality but remain static after deployment: pronunciation errors on out-of-vocabulary proper nouns persist unless the model is retrained.
Aslema is a system developed for the NADI 2026 Shared Task 5, which involves intent recognition and slot filling. The team evaluated four omni LLMs in a zero‑shot setting and found that fine‑tuned models consistently outperform zero‑shot inference. They further improved performance by augmenting data with culturally grounded Tunisian Derja utterances generated by an LLM and synthetic speech produced via voice cloning, achieving top‑ranked results on the official test set.
arXiv:2607. 10092v1 Announce Type: cross Abstract: Spoken language models (SLMs) unify speech perception and reasoning, but adapting them to sensitive domains is underexplored, especially when the original training data is inaccessible and the use case demands multilingual, spoken-query interaction.
arXiv:2609.24903v1 Announce Type: new Abstract: Tone languages constitute over 50-70% of the world's languages, but the vast majority are low-resource, lacking the large transcribed corpora needed fo...