The relative contributions of non-spectral cues to static and dynamic spectral model identification of Korean monophthong signals in Seoul Corpus
0
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
Though the importance of spectral characteristics at the steady-state central sections of Korean monophthongal signals in the hVd syllable has been amply reported in the literature, it has been rarely studied whether dynamic spectral measurements sampled multiply across the temporal dimension can better characterize Korean vowels in spontaneous speech than static spectral measurements at a (steady-state) central section. Furthermore, the perceptual influence of non-spectral cues on the spectral properties of vowels in vowel perception has been frequently reported in the literature, but few reports have been released on the relative amount of the individual perceptual contributions of non-spectral cues (e.g., gender, speaking rate, duration, F0, place and manner of the flanking phones, etc.) on the spectral properties of vowels in vowel perception. Neural Network pattern recognition modeling on spectral identification of Korean monophthong signals in Seoul Corpus showed that dynamic spectral models fitted to non-spectral cues, identified vowel signals better than static spectral models. Furthermore, flanking phone identities, and manner and place of flanking phones (i.e., coarticulation information) were the most contributive to spectral vowel identification. However, F0, speaking rate, duration, gender, and speaker’s age showed little or almost no contribution.
Abstract
Though the importance of spectral characteristics at the steady-state central sections of Korean monophthongal signals in the hVd syllable has been amply reported in the literature, it has been rarely studied whether dynamic spectral measurements sampled multiply across the temporal dimension can better characterize Korean vowels in spontaneous speech than static spectral measurements at a (steady-state) central section. Furthermore, the perceptual influence of non-spectral cues on the spectral properties of vowels in vowel perception has been frequently reported in the literature, but few reports have been released on the relative amount of the individual perceptual contributions of non-spectral cues (e.g., gender, speaking rate, duration, F0, place and manner of the flanking phones, etc.) on the spectral properties of vowels in vowel perception. Neural Network pattern recognition modeling on spectral identification of Korean monophthong signals in Seoul Corpus showed that dynamic spectral models fitted to non-spectral cues, identified vowel signals better than static spectral models. Furthermore, flanking phone identities, and manner and place of flanking phones (i.e., coarticulation information) were the most contributive to spectral vowel identification. However, F0, speaking rate, duration, gender, and speaker’s age showed little or almost no contribution.
참고문헌 (34)
- ASSMANN, PETER F., "Vowel Inherent Spectral Change", pp.1~6 (2013), Springer-Verlag
- ". Version 6.0.37" (2018)[URL]
- "Stochastic gradient descent (v.2)" (2010)[URL]
- BROWMAN, CATHERINE P., "Papers in Laboratory Phonology I: Between the Grammar and Physics of Speech", pp.341~376 (1990), CUP
- BYRD, DANI, "Relations of sex and dialect to reduction", Speech Communication, 15, pp.39~54 (1994)
- DEMSAR, JANEZ, "Orange: Data mining toolbox in python", Journal of Machine Learning Research, 14, pp.2349~2353 (2013)
- ENGSTRAND, OLLE, "Articulatory correlates of stress and speaking rate in Swedish VCV utterances", Journal of the Acoustical Society of America, 83, pp.1863~1875 (1988)
- FANT, GUNNAR, "Acoustic Theory of Speech Production" (1960), Mouton
- FANT, GUNNAR, "A note on vocal tract size factors and non-uniform F-pattern scalings", Laboratory Quarterly Progress and Status Report, 4, pp.22~30 (1966)
- FUJISAKI, HIROYA, "The influence of various factors on the identification and discrimination of synthetic speech sounds", Paper Presented at the 6th International Congress on Acoustics (1968)
- GAY, THOMAS, "Effect of speaking rate on vowel formant movements", Journal of Acoustical Society of America, 63, pp.223~230 (1978)
- GOLDSTEIN, URSULA, "An Articulatory Model for the Vocal Tracts of Growing Children", PhD, pp.1980
- HENTON, CAROLINE, "New Departures in Linguistics", pp.27~55 (1992), Garland Publishing Co
- HILLENBRAND, JAMES M., "Vowel Inherent Spectral Change", pp.9~30 (2013), Springer Verlag
- HILLENBRAND, JAMES M., "Acoustic characteristics of American English vowels", Journal of Acoustical Society of America, 97, pp.3099~3111 (1995)
- HILLENBRAND, JAMES M., "Effects of consonant environment on vowel formant patterns", Journal of the Acoustical Society of America, 109, pp.748~763 (2000)
- HIRATA, YUKARI, "The effects of speaking rates and vowel duration on formant movements in Japanese", Proceedings of the 2003 Texas Linguistics Society Conference: Coarticulation in Speech Production and Perception, pp.73~85 (2004)
- 홍순현, "Perceptual Influence of Non-Spectral Cues on Spectral Properties of Korean Vowel Signals in Seoul Corpus: A Neural Network Modeling Study", 현대문법연구, (102), pp.135~164 (2019), 현대문법학회[DOI]
- KINGMA, DIEDERIK, "Adam: A method for stochastic optimization. ArXiv Preprint ArXiv:1412.6980", ~ (2014)
- JOHNSON, KEITH, "The role of perceived speaker identity in F0 normalization of vowels", Journal of the Acoustical Society of America, 88, pp.642~654 (1990)
- JOHNSON, KEITH, "The Handbook of Speech Perception", pp.363~389 (2008), Blackwell Publishing
- LECUN, YANN, "Efficient backprop", Proceedings of Neural Networks: Tricks of the Trade, pp.9~50 (1996)
- LEHISTE, ILSE, "Vowel and speaker identification in natural and synthetic speech", Language and Speech, 16, pp.356~364 (1973)
- LEHISTE, ILSE, "Transitions, glides, and diphthongs", Journal of Acoustical Society of America, 33, pp.268~277 (1961)
- LINDBLOM, BJORN, "Spectrographic study of vowel reduction", Journal of Acoustical Society of America, 35, pp.1773~1781 (1963)
- LINDBLOM, BJORN, "On the role of formant transitions in vowel recognition", Journal of the Acoustical Society of America, 42, pp.830~843 (1967)
- MILLER, ROGER L., "Auditory tests with synthetic vowels", Journal of Acoustical Society of America, 25, pp.114~121 (1953)
- MOON, SEUNG-JAE, "Interaction between duration, context, and speaking style in English stressed vowels", Journal of Acoustical Society of America, 96, pp.40~55 (1994)
- NEAREY, TERRANCE M., "Modeling the role of vowel inherent spectral change in vowel identification", Journal of Acoustical Society of America, 80, pp.1297~1308 (1986)
- "Unsupervised feature learning and deep learning. Lecture note" (2015)[URL]
- NORDSTRÖ M, PER-ERIK, "Female and infant vocal tracts simulated from male area functions", Journal of Phonetics, 5, pp.81~92 (1977)
- PETERSON, GORDON E., "Control methods used in a study of vowels", Journal of Acoustical Society of America, 24, pp.175~184 (1952)
- RUMELHART, DAVID E., "Learning representations by back-propagating errors", Nature, 323, pp.533~536 (1986)
- SLAWSON, A. WAYNE, "Vowel quality and musical timbre as functions of spectrum envelope and fundamental frequency", Journal of the Acoustical Society of America, 43, pp.87~101 (1968)