On the Use/Misuse of the Term 'Phoneme'

Moore, Roger K.; Skidmore, Lucy

doi:10.48550/arxiv.1907.11640

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inference procedure of prosodic HDP-HLM enables the estimation of the structure from time-series data. Therefore, we call the unsupervised machine learning method based on prosodic HDP-HLM as prosodic DAA, in the same way as the unsupervised learning method that is based on the original HDP-HLM is called NPB-DAA 3 .…”

Section: Prosodic Daa and Prosody Featuresmentioning

confidence: 99%

“…The data comprised 60 recorded audio files in which a female native Japanese speaker read 30 artificially constructed sentences aloud twice at a natural speed. The sentences comprised 3 The source code of Prosodic DAA is available at https://github.com/EmergentSystemLabStudent/Prosodic-DAA 4 Japanese vowel native speech dataset: https://github.com/EmergentSystemLabStudent/aioi dataset five words {aioi, aue, ao, ie, uo}, which consisted of five Japanese vowels {a, i, u, e, o} representing {ä, i, W B , e fl , o fl } in phonetic symbols respectively. By combining the 5 words, the 30 sentences included 25 two-word sentences, e.g., "aioi," "aue ie," and "uo ao," and five three-word sentences i.e., "aioi uo ie," "aue ao ie," "ao ie ao," "ie uo," and "uo aue ie," were prepared.…”

Section: A Conditionsmentioning

confidence: 99%

See 1 more Smart Citation

Double Articulation Analyzer With Prosody for Unsupervised Word and Phone Discovery

Okuda

Ozaki

Komura

et al. 2023

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Word and phone discovery are important tasks in the language development of human infants. Infants acquire words and phones from unsegmented speech signals using segmentation cues such as distributional, prosodic, and cooccurrence information. Many pre-existing computational models designed to represent this process tend to focus on distributional or prosodic cues. In this study, we propose a nonparametric Bayesian probabilistic generative model called the prosodic hierarchical Dirichlet process-hidden language model (prosodic HDP-HLM) designed to perform simultaneous phone and word discovery from continuous speech signals encoded as timeseries data that may exhibit a double articulation structure. Prosodic HDP-HLM, as an extension of HDP-HLM, considers both prosodic and distributional cues within a single integrative generative model. We further propose a prosodic double articulation analyzer (Prosodic DAA) based on an inference procedure derived for prosodic HDP-HLM. We conducted three experiments on different types of datasets, including, Japanese vowel sequence, utterances for teaching object names and features, and utterances following Zipf's law, and the results demonstrated the validity of the proposed method. The results show that the Prosodic DAA successfully used prosodic cues and was able to discover words directly from continuous human speech using distributional and prosodic information in an unsupervised manner, outperforming a method that solely used distributional cues. In contrast, the phone discovery performance did not improve. We also show that prosodic cues contributed to word discovery performance more when the word frequency was distributed more naturally, i.e., following Zipf's law.

show abstract

Section: Prosodic Daa and Prosody Featuresmentioning

confidence: 99%

Section: A Conditionsmentioning

confidence: 99%