순환 신경망을 활용한 조음 정보와 음운 자질의 연결 연구
Mapping of Articulatory Information into Phonological Features Using a Recurrent Neural Network
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study attempted to link continuous and dynamic articulatory information to categorical phonological feature representations through a neural network model. The Long Short-Term Memory (LSTM) model was used in the current paper, which is a type of recurrent neural network including temporal information connections. The test results of the LSTM model mapping muscular activation into phonological features show that (i) gradient values of phonological features are derived from the degree of activation of the tongue muscles, which determines the movement and shape of the tongue, and (2) the LSTM model can systematically capture vowels' co-articulatory effect on consonants.
Abstract
This study attempted to link continuous and dynamic articulatory information to categorical phonological feature representations through a neural network model. The Long Short-Term Memory (LSTM) model was used in the current paper, which is a type of recurrent neural network including temporal information connections. The test results of the LSTM model mapping muscular activation into phonological features show that (i) gradient values of phonological features are derived from the degree of activation of the tongue muscles, which determines the movement and shape of the tongue, and (2) the LSTM model can systematically capture vowels' co-articulatory effect on consonants.
참고문헌 (37)
- 이상도, "제약연접이론의 필요성-구개음화를 중심으로", 언어과학, 19(4), pp.185~201 (2012), 한국언어과학회
- Bateman, N., "A Crosslinguistic Investigation of Palatalization", 박사, pp.2007
- Biasutto–Lervat, T, "Phoneme-to-articulatory Mapping Using Bidirectional Gated RNN", Proceedings of Interspeech 2018-19th Annual Conference of the International Speech Communication Association (2018)
- Boersma, P., "Neural Network Models for Phonology and Phonetics", Journal of Language Modelling, 8(1), pp.103~177 (2020)[DOI]
- Browman, C. P, "Phonetic Linguistics: Essays in Honor of Peter Ladefoged", pp.35~53 (1984), Academic Press
- Browman, C. P, "Gestural Specification Using Dynamically-defined Articulatory Structures", Journal of Phonetics, 18, pp.299~320 (1990)[DOI]
- Browman, C. P, "Papers in Laboratory Phonology I: Between the Grammar and Physics of Speech", pp.341~376 (1990), Cambridge University Press
- Beguš, G, "Identity-Based Patterns in Deep Convolutional Networks:Generative Adversarial Phonology and Reduplication", Transactions of the Association for Computational Linguistics, 9, pp.1196~1212 (2021)[DOI]
- Chen, M, "Predictive Power in Phonological Description", Lingua, 32, pp.173~191 (1973)[DOI]
- Flemming, E, "Auditory Representations in Phonology" (2002), Routledge
- Fowler, C.A, "Coarticulation and Theories of Extrinsic Timing", Journal of Phonetics, 8, pp.113~133 (1980)[DOI]
- Garvin, K, "A Q-theoretic Approach to 0Distinctive Subsegmental Timing", Proceedings of the Linguistic Society of America, 3(1), pp.1~13 (2018)[DOI]
- Gerfen, C, "Phonology and Phonetics in Coatzospan Mixtec" (1999), Kluwer Academic Publishers
- Goldstein, L., "Syllable Structure as Coupled Oscillator Modes: Evidence from Georgian vs. Tashlhiyt Berber", Proceedings of the XVIth International Congress of Phonetic Sciences, pp.241~244 (2007)
- Haeri, N, "A Linguistic Innovation of Women in Cairo", Language Variation and Change, 6, pp.87~112 (1994)[DOI]
- Hardcastle, W. J, "Some Phonetic and Syntactic Constraints on Lingual Coarticulation During", kl, Speech Communication, pp.1985, 4[DOI]
- Inkelas, S, "Contour Segments and Tones in (sub) Segmental Agreement by Correspondence", 21st Manchester Phonology Meeting (2013), University of Manchester
- Inkelas, S, "Re-representing Phonology: Consequences of Q Theory", Proceedings of the North East Linguistic Society, 46, pp.1~10 (2016), GLSA Publications
- Inkelas, S, "Looking into Segments", Proceedings of the 2016 Annual Meeting on Phonology, 4, pp.1~10 (2017)
- Jang, H., "Articulatory Knowledge in Phonological Computation", 박사, pp.2020
- 강경심, "A Phonetic Account of Korean Affricates: Neutralization with a Palatal Glide", 언어과학, 16(1), pp.169~186 (2009), 한국언어과학회
- King, S, "Detection of Phonological Features in Continuous Speech Using Neural Networks", Computer Speech & Language, 14, pp.333~353 (2000)[DOI]
- Kochetov, A, "Companion to Phonology 3", pp.1666~1690 (2011), Wiley Blackwell
- Lionnet, F., "Subphonemic Teamwork: A Typology and Theory of Cumulative Effects in Phonology", 박사, pp.2016
- Lionnet, F, "A Theory of Subfeatural Representations: The Case of Rounding Harmony in Laal", Phonology, 34(3), pp.523~564 (2017)[DOI]
- Lloyd, J. E., "Soft Tissue Biomechanical Modeling for Computer Assisted Surgery", pp.355~394 (2012), Springer
- Löfqvist, A, "Interarticulator Programming in VCV Sequences: Lip and Tongue Movements", Journal of the Acoustical Society of America, 105(3), pp.1864~1876 (1999)[DOI]
- Mielke, J., "The Emergence of Distinctive Features" (2008), Oxford University Press
- Nam, H, "Syllable-level Intergestural Timing Model: Split-gesture Dynamics Focusing on Positional Asymmetry and Moraic Structure", Laboratory Phonology, 9, pp.483~506 (2007)
- Schwarz, M., "Recent Advances in Q Theory: Segment Strength", Proceedings of the Linguistic Society of America, 4(1), pp.1~14 (2019)[DOI]
- Shih, S. S, "A Subsegmental Correspondence Approach to Contour Tone (dis)Harmony Patterns", Proceedings of the 2013 Meeting on Phonology (2014)
- Smith, C, "Emergent Gestural Scores in a Recurrent Neural Network Model of Vowel Harmony", Proceedings of the Society for Computation in Linguistics, 4(1), pp.61~70 (2021)[DOI]
- Smolensky, P, "Gradient Symbolic Representation in Grammar: The Case of French Liason", 석사, pp.2016
- Smolensky, P., "Optimization and Quantization in Gradient Symbol Systems: A Framework for Integrating the Continuous and the Discrete in Cognition", Cognitive Science, 38(6), pp.1102~1138 (2014)[DOI]
- Stone, M, "The Handbook of Phonetic Sciences", pp.11~32 (1997), Blackwell
- Toutios, A., "Illustrating the Production of the International Phonetic Alphabet Sounds using Fast Real-Time Magnetic Resonance Imaging", Interspeech, pp.2428~2432 (2016)
- Zsiga, E. C., "Features, Gestures, and the Temporal Aspects of Phonological Organization", 박사, pp.1993