Predicting pre- and post-vocalic stop consonant place from the vowel in a Korean spontaneous speech corpus
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
A neural network model was trained on temporal F2 frequencies sampled singly or doubly along the first half of vowel articulation in CVX tokens and the second half in XVC in a Korean spontaneous speech corpus to predict pre- and post-vocalic stop place, respectively. Model performance on temporal F2 frequencies sampled doubly at vowel onset/offset and target constituted the best cues for pre- and post-vocalic stop place, though prevocalic place was predicted slightly better than postvocalic place. Then, secondary cues were added to the dynamic F2 predictors for further training. The individual contributions of speaking rate, F0, gender, vowel duration, and static F1 and F3 frequencies sampled singly at vowel onset/offset were not as big as the temporal F1 and F3 frequencies sampled at vowel onset/offset and target, the latter of which enhanced model prediction substantially. The dynamic F1 and F3 predictors facilitated postvocalic place prediction more than prevocalic place prediction. Vowel identity enhanced prevocalic place prediction substantially but did not enhance postvocalic place prediction as much. This was due to the observation that F1/F2 transitions of all vowel categories were substantially more centralized in the F1/F2 vowel space at vowel offset than at onset or target. Vowel quality became less distinctive at vowel offset. Nevertheless, temporal formant samples plus vowel identity constituted the best cues for stop place.
Abstract
A neural network model was trained on temporal F2 frequencies sampled singly or doubly along the first half of vowel articulation in CVX tokens and the second half in XVC in a Korean spontaneous speech corpus to predict pre- and post-vocalic stop place, respectively. Model performance on temporal F2 frequencies sampled doubly at vowel onset/offset and target constituted the best cues for pre- and post-vocalic stop place, though prevocalic place was predicted slightly better than postvocalic place. Then, secondary cues were added to the dynamic F2 predictors for further training. The individual contributions of speaking rate, F0, gender, vowel duration, and static F1 and F3 frequencies sampled singly at vowel onset/offset were not as big as the temporal F1 and F3 frequencies sampled at vowel onset/offset and target, the latter of which enhanced model prediction substantially. The dynamic F1 and F3 predictors facilitated postvocalic place prediction more than prevocalic place prediction. Vowel identity enhanced prevocalic place prediction substantially but did not enhance postvocalic place prediction as much. This was due to the observation that F1/F2 transitions of all vowel categories were substantially more centralized in the F1/F2 vowel space at vowel offset than at onset or target. Vowel quality became less distinctive at vowel offset. Nevertheless, temporal formant samples plus vowel identity constituted the best cues for stop place.
참고문헌 (30)
- ABUOUDEH, MOHAMMAD, "Vowel length impact on locus equation parameters : An investigation on Jordanian Arabic", Interspeech, 2014, pp.184~188 (2014)
- ABUOUDEH, MOHAMMAD, "The impact of vowel length contrasts on locus equations and their implication", Paper presented at Dinafon 2014 (2014)
- ". Version 6.0.37" (2018)[URL]
- BRANCAZIO, LAWRENCE, "On the relevance of locus equations for production and perception of stop consonants", Perception and Psychophysics, 60, pp.24~50 (1998)
- BROAD, DAVID J., "Piecewise-planar Representation of Vowel Formant Frequencies", Journal of the Acoustical Society of America, 62, pp.1467~1473 (1977)
- CHO, TAEHONG, "Variation and universals in VOT : Evidence from 18 languages", Journal of Phonetics, 27, pp.207~229 (1999)
- DELATTRE, PIERRE C., "Acoustic loci and transitional cues for consonants", Journal of the Acoustical Society of America, 27, pp.769~777 (1955)
- DEMSAR, JANEZ, "Orange : Data mining toolbox in python", Journal of Machine Learning Research, 14, pp.2349~2353 (2013)
- FANT, GUNNAR, "Speech Sounds and Features" (1973), MIT Press
- FOWLER, CAROL A, "Invariants, specifiers, cues : An investigation of locus equations as information for place of articulation", Perception and Psychophysics, 55, pp.597~610 (1994)
- GAY, THOMAS, "Effect of speaking rate on vowel formant movements", Journal of Acoustical Society of America, 63, pp.223~230 (1978)
- HERRMANN, FRANK, "Speaker sex effects on temporal and spectro-temporal measures of speech", Journal of the International Phonetic Association, 44, pp.59~74 (2014)
- HILLENBRAND, JAMES, "Acoustic characteristics of American English vowels", Journal of the Acoustical Society of America, 97, pp.3099~3111 (1995)
- 홍순현, "Systematic centralized reduction at the offset of Korean monophthong signals in spontaneous speech", 음성음운형태론연구, 26(3), pp.545~565 (2020), 한국음운론학회[DOI]
- 홍순현, "Roles of temporal patterns of vowel-intrinsic cues in model identification of Korean vowels in spontaneous speech", 음성음운형태론연구, 27(2), pp.321~351 (2021), 한국음운론학회[DOI]
- 홍순현, "Roles of dynamic properties of F2 and vowel identity in predicting preceding consonant place in CVX in Korean spontaneous speech", 음성음운형태론연구, 28(1), pp.141~167 (2022), 한국음운론학회[DOI]
- 홍순현, "Roles of dynamic patterns of lower formants, vowel identity, and gender in predicting postvocalic consonant place in Korean spontaneous speech", 음성음운형태론연구, 29(2), pp.211~246 (2023), 한국음운론학회[DOI]
- KEWLEY-PORT, DIANE, "Measurement of formant transitions in naturally produced stop consonant-vowel syllables", Journal of the Acoustical Society of America, 72, pp.379~389 (1982)
- LIBERMAN, ALVIN M, "The role of consonant-vowel transitions in the perception of the stop and nasal consonants", Psychological Monographs : General and Applied, 68, pp.1~13 (1954)
- MCLEOD, AMY, "Categorization : A direct replication of Sussman, McCaffrey, and Matthews", Contemporary Issues in Communication Science and Disorders, 28, pp.98~103 (2001)
- O’SHAUGHNESSY, DOUGLAS, "The effects of speaking rate on formant transitions in French synthesis-by-rule", IEEE International Conference on Acoustics, Speech and Signal Processing, 11, pp.2027~2030 (1986)
- RHONE, ARIANE E., "Modified locus equations categorize stop place in a perceptually realistic time frame", Journal of the Acoustical Society of America, 131, pp.EL487~EL491 (2012)
- SCHOUTON, M. E. H., "Vowel segments in consonantal contexts: A spectral study of coarticulation - part I", Journal of Phonetics, 7, pp.1~23 (1979)
- SUSSMAN, HARVEY M, "Linear correlates in the speech signal : The orderly output constraint", Behavioral and Brain Science, 21, pp.241~259 (1998)
- SUSSMAN, HARVEY M, "An investigation of locus equations as a source of relational invariance for stop place categorization", Journal of the Acoustical Society of America, 90, pp.1309~1325 (1991)
- SUSSMAN, HARVEY M, "A crosslinguistic investigation of locus equations as a phonetic descriptor for place of articulation", Journal of the Acoustical Society of America, 94, pp.1256~1268 (1993)
- SUSSMAN, HARVEY M, "An investigation of stop place of articulation as a function of syllable position : A locus equation perspective", Journal of the Acoustical Society of America, 101, pp.2826~2838 (1997)
- WEISMER, GARY, "Effects of speaking rate on second formant trajectories of selected vocalic nuclei", The Journal of Acoustical Society of America, 113, pp.3362~3378 (2003)
- 윤태진, "이층위 신경망 모형을 사용한 포먼트 궤적 기반 모음 유형 분류", 음성음운형태론연구, 25(1), pp.95~112 (2019), 한국음운론학회[DOI]
- 윤원희, "The Korean Corpus of Spontaneous Speech", 말소리와 음성과학, 7(2), pp.103~109 (2015), 한국음성학회[DOI]