phonetics

This study investigates temporal organization in bilingual political speech, revealing that consonant-based timing metrics are speaker-specific while vowel-based metrics are language-dependent, with French exhibiting longer and more variable vowels.

This paper explores how intonation and lexical tone interact in Mandarin varieties, using boundary phenomena to examine f0 cues for sentence-level functions like questions versus statements, and discusses theoretical models.

This paper presents PiDA, a phonetically-informed data augmentation method for Vietnamese speech translation that improves robustness by generating ASR-like corruptions using phonetic word embeddings, achieving up to +2.04 BLEU on noisy outputs.

This paper investigates whether pretrained self-supervised speech models like Wav2Vec2 and HuBERT can accurately recognize click consonants, which are rare in training data, by fine-tuning on Khoisan languages. Results show the models recognize clicks more accurately than non-clicks, indicating generalization to uncommon phonemes.

This paper compares existing Dutch syllabification algorithms and introduces a deep learning model that combines phonetic and orthographic information, achieving a slight improvement in word accuracy.

This study uses ultrasound tongue imaging data from 36 speakers to show that individual articulatory strategies for producing the palatal vowel /i/ systematically influence acoustic formant dynamics in diphthongs, linking tongue movement patterns to formant transition timing and steepness.