Speech recognition rates and acoustic analyses of English vowels produced by Korean students
1
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
English vowels play an important role in verbal communication. However, Korean students tend to experience difficulty pronouncing a certain set of vowels despite extensive education in English. The aim of this study is to apply speech recognition software to evaluate Korean students’ pronunciation of English vowels in minimal pair words and then to examine acoustic characteristics of the pairs in order to check their pronunciation problems. Thirty female Korean college students participated in the recording. Speech recognition rates were obtained to examine which English vowels were correctly pronounced. To compare and verify the recognition results, such acoustic analyses as the first and second formant trajectories and durations were also collected using Praat. The results showed an overall recognition rate of 54.7%. Some students incorrectly switched the tense and lax counterparts and produced the same vowel sounds for qualitatively different English vowels. From the acoustic analyses of the vowel formant trajectories, some of these vowel pairs were almost overlapped or exhibited slight acoustic differences at the majority of the measurement points. On the other hand, statistical analyses on the first formant trajectories of the three vowel pairs revealed significant differences throughout the measurement points, a finding that requires further investigation. Durational comparisons revealed a consistent pattern among the vowel pairs. The author concludes that speech recognition and analysis software can be useful to diagnose pronunciation problems of English-language learners.
Abstract
English vowels play an important role in verbal communication. However, Korean students tend to experience difficulty pronouncing a certain set of vowels despite extensive education in English. The aim of this study is to apply speech recognition software to evaluate Korean students’ pronunciation of English vowels in minimal pair words and then to examine acoustic characteristics of the pairs in order to check their pronunciation problems. Thirty female Korean college students participated in the recording. Speech recognition rates were obtained to examine which English vowels were correctly pronounced. To compare and verify the recognition results, such acoustic analyses as the first and second formant trajectories and durations were also collected using Praat. The results showed an overall recognition rate of 54.7%. Some students incorrectly switched the tense and lax counterparts and produced the same vowel sounds for qualitatively different English vowels. From the acoustic analyses of the vowel formant trajectories, some of these vowel pairs were almost overlapped or exhibited slight acoustic differences at the majority of the measurement points. On the other hand, statistical analyses on the first formant trajectories of the three vowel pairs revealed significant differences throughout the measurement points, a finding that requires further investigation. Durational comparisons revealed a consistent pattern among the vowel pairs. The author concludes that speech recognition and analysis software can be useful to diagnose pronunciation problems of English-language learners.
참고문헌 (24)
- "Praat: Doing phonetics by computer (version 6.2)" (2021)[URL]
- Davenport, M., "Introducing phonetics and phonology" (1998), Hodder Arnold
- s really tense? The mapping between articulation and acoustics, "Lingua", 2012, 810~821
- Delattre, P. C., "Acoustic loci and transitional cues for consonants", Journal of the Acoustical Society of America, 27(4), pp.769~773 (1955)
- Kennedy, R., "The Cambridge handbook of phonetics", pp.682~706 (2022), Cambridge University Press
- 이서희, "The relationship between vowel production and proficiency levels in L2 English produced by Korean EFL learners", 말소리와 음성과학, 11(2), pp.1~13 (2019), 한국음성학회[DOI]
- Millett, P., "Accuracy of speech-to-text captioning for students who are deaf or hard of hearing. Journal of Educational", Pediatric &(Re)Habilitative Audiology, 25, pp.1~13 (2021)
- "English vowels. Linguistics 205 course notes of practical phonetics" (2006)[URL]
- Pickett, J. M., "The sounds of speech communication : A primer of acoustic phonetics and speech perception(Perspectives in Audiology Series)" (1980), University Park Press
- "R: A language and environment for statistical computing (version 4.1.0)" (2021)[URL]
- "Generalised additive mixed models for dynamic analysis in linguistics: A practical introduction" (2017)[URL]
- "Overview of GAMM analysis of time series data" (2015)[URL]
- Weckwerth, J., "The Cambridge handbook of phonetics", pp.40~64 (2022), Cambridge University Press
- Wood, S. N., "Generalised additive models: An introduction with R" (2006), CRC Press
- Yang, B., "Development of vowel normalization procedures : English and Korean", Doctor, pp.1990
- Yang, B., "A comparative study of American English and Korean vowels produced by male and female speakers", Journal of Phonetics, 24(2), pp.245~261 (1996)
- Yang, B., "Discrimination of synthesized English vowels by American and Korean listeners", Speech Sciences, 13(1), pp.7~27 (2006)
- 양병곤, "미국인 남성이 발음한 영어 모음의 포먼트 궤적", 말소리와 음성과학, 1(3), pp.65~72 (2009), 한국음성학회
- 양병곤, "Formant Trajectories of English High Tense and Lax Vowels Produced by Korean and American Speakers", 언어, 35(2), pp.407~423 (2010), 한국언어학회[DOI]
- 양병곤, "대학생들이 또렷한 음성과 대화체로 발화한 영어문단의 구글음성인식", 말소리와 음성과학, 9(4), pp.43~50 (2017), 한국음성학회[DOI]
- 양병곤, "A comparison of normalized formant trajectories of English vowels produced by American men and women", 말소리와 음성과학, 11(1), pp.1~8 (2019), 한국음성학회[DOI]
- 양병곤, "An evaluation of Korean students' pronunciation of an English passage by a speech recognition application and two human raters", 말소리와 음성과학, 12(4), pp.19~25 (2020), 한국음성학회[DOI]
- Yang, B., "The Cambridge handbook of phonetics", pp.261~284 (2022), Cambridge University Press
- Yang, B., "Perception and production of English vowels by American males and females", Australian Journal of Linguistics, 35(2), pp.121~141 (2015)