Speech foundation models are primarily evaluated with task-level metrics, which do not establish whether language-specific phonological patterns are encoded or faithfully reproduced. This dissertation asks what evidence is required to distinguish recoverable acoustic or distributional information from phonological generalization in speech models. Assamese Advanced Tongue Root (ATR) vowel harmony provides the primary test case because its production pattern combines acoustic vowel contrasts with long-distance, directional dependencies. Four interconnected studies examine (i) the acoustic-phonetic realization of ATR in human speech, (ii) generative learning with fiwGAN, (iii) process-level probing of frozen self-supervised speech models, and (iv) phonological faithfulness in multilingual TTS. Results so far show that ATR-and harmony-correlated information can be highly recoverable even when model behavior does not exhibit the structural signatures expected of Assamese harmony. The dissertation, therefore, develops evaluation criteria that distinguish phonetic recoverability from evidence for phonological process encoding, with implications for speech technologies in typologically diverse and low-resource languages.
Structured phonological representations provide an interpretable alternative to generic speech embeddings, but existing models are largely trained on adult speech. We adapt PhonoQ-2.0 to child speech using CHILDES-Aligned data and compare three alignment-supervision conditions (Adult, Adult+Child, and Child-only) acros...
Abner Hernandez, T. A. Vergara, Andreas K. Maier et al.· 0 citations
Persistent pronunciation difficulties remain evident even among advanced learners of English, yet it is still unclear whether such patterns reflect stabilized interlanguage representations or merely limited responsiveness to short-term instruction. This study investigates recurrent phonetic and phonological errors amon...
T. Al-Shamayleh, Mohammad Hanaqtah, M. Al-Smaihyeen et al.· World Journal of English Lan...· 0 citations
How much phonological knowledge do language models (LMs) possess about Chinese characters, and how is this knowledge represented and used? We introduce PinyinBench, a controlled benchmark covering homophones, phonological features (initials, finals, and tones), and polyphonic characters. We investigate 17 text-only and...
German is a morphologically rich language whose syllable structure is exceptionally well-predicted by the Knuth--Liang hyphenation algorithm. We ask whether phonologically informed tokenization can serve as a competitive target for end-to-end speech recognition. We compare three tokenizer families on the Omnilingual AS...
Christopher Witzl, Tobias Bocklet, Korbinian Riedhammer· Conference on Empirical Meth...· 0 citations
Phoneme-level models transcribe or generate speech as a sequence of phonemes, the smallest sound units that distinguish words. These models enable fine-grained pronunciation control and understanding, yet often fail on input that does not match any single training language, such as speech alternating between two langua...
Moran Yanuka, Raja Giryes, M. Alper· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.