№2, 2016
DIALECTS RECOGNITION BASED ON ACOUSTIC MODEL
Regional dialect recognition is important in the field of speech technologies. It is widely used in telephone reference systems, adapting the output synthesized speech in dialog systems, and also in forensics for profiling speaker in judicial or military situations, etc. The article describes different approaches that allow the usage of multiple information sources from the acoustic signal for the construction of dialects recognition system. In particular, acoustic, prosodic, phonetic, and phonotactic approaches are considered. (pp.34-38)
Keywords: dialects recognition, acoustic model, speech signal, UBM-GMM model.
References
- Clark J. An Introduction to phonetics and phonology. Oxford: Blackwell Publishing, 2007, 504 p.
- Biadsy F. Automatic dialect and accent recognition and its application to speech recognition: Ph.D. dissertation. Columbia University, 2011, 171 p.
- Omar M.K., Pelecanos J. A novel approach to detecting non-native speakers and their native language / Proc. of IEEE ICASSP, 2010, pp.4398–4401.
- Roy P., Das P.K. Language ıdentification of Indian languages based on gaussian mixture models // International Journal of Wisdom Based Computing, 2011, vol.1, no.3, pp.54–59.
- Liu M.K., Xu B., Huang T.Y., Deng Y.G., Li C.R. Mandarin accent adaptation based on context-ındependent/context-dependent pronunciation modeling / Proc. of ICASSP, 2000, vol.2, pp.1025–1028.
- Hazen, T., Zue, V. Segment-based automatic language ıdentification // Journal of the Acoustic Society of America, 1997, vol.101, no.4, pp.2323–2331.
- Akmajian A., Demers R.A., Farmer A.K, Harnish R.M. Linguistics: an introduction to language and communication. Massachusetts: MIT Press, 2001, 604 p.
- Nerbonne J. Linguistic variation and computation / Proc. of the 10th conference on European chapter of the Association for Computational Linguistics, 2003, vol.1, pp.1–3.
- Petyt K.M. The study of dialect: an introduction to dialectology. London: Westview Press, 1980, 235 p.
- Dictionary of Russian folk dialects, vol. 1-43. M. A .: Science, 1965, p. 306.
- Bromley S.V., Bulatova L.N., Zakharova K.F. Russian dialectology. M .: Education, 1989, p. 223
- Order of the President of the Republic of Azerbaijan on the "Approval of the State Program on the use of the Azerbaijani language in accordance with the requirements of globalization and the development of linguists in the country", "Azerbaijan" newspaper, Baku, 2013, April 9.
- Shiraliyev M.Sh. Dialectic fundamentals of the Azerbaijani national literal language. M .: Publishing House of the USSR Academy of Sciences, 1958, pp.78–84.
- Dialectological dictionary of the Azerbaijani language. Baku: "East-West", 2007, p.568
- Bayramov I. Vocabulary of the dialect of the Western Azerbaijan. Baku: "Science and Education", 2011, p.440
- Kazimov G. The study of the history of dialects and accents // Problems of philology, 2014, no.1, pp.3–27.
- Teixeira C., Trancoso I., Serralheiro A. Accent identification / Proc. of INTERSPEECH, 1996, vol.3, pp.1784–1787.
- Hanani A., Russell M.J., Carey M.J. Human and computer recognition of regional accents and ethnic groups from british english speech //Computer Speech and Language, 2013, vol.27, no.1, pp.59–74.
- Huang R., Hansen J.H.L., Angkititrakul P. Dialect/accent classification using unrestricted audio // IEEE Trans. on Audio, Speech and Language Processing, 2007, vol.15, no.2, pp.453–464.
- Mporas I., Ganchev T., Fakotakis N. Phonotactic recognition of greek and cypriot dialects from telephone speech // SETN 2008, Advances in Artificial Intelligence, Lecture Notes in Computer Science. Berlin: Springer-Verlag, 2008, pp.173–181.
- Tong, R., Ma, B., Li, H., Chng, E.S. Integrating acoustic, prosodic and phonotactic features for spoken language ıdentification / Proc. of IEEE ICASSP, 2006, pp.205–208.
- Campbell W. M., Singer E., Torres-Carrasquillo P.A., Reynolds D.A. Language recognition with support vector machines / Proc. of Odyssey, 2004, pp.285–288.
- Braun J., Levkowitz H. Automatic language ıdentification with perceptually guided training and recurrent neural networks / Proc. of the 5th International Conference on Spoken Language Processing (ICSLP), 1998, pp.3201–3205.
- Ghesquiere P.J., Compernolle D.V. Flemish accent ıdentification based on formant and duration features // Proc. of ICASSP, 2002, pp.749–752.
- Lin C.Y., Wang H.C. Fusion of phonotactic and prosodic knowledge for language ıdentification / Proc. of the 9th International Conference on Spoken Language Processing (ICSLP), 2006, pp.425–428.
- Farinas J., Pellegrino F., Rouas J.L., Andre-Obrecht R. Merging segmental and rhythm features for automatic language identification / Proc. of IEEE ICASSP, 2002, pp.753–756.
- Rouas J.-L., Farinas J., Pellegrino F., Andre-Obrecht R. Modeling prosody for language identification on read and spontaneous speech / IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003, vol.6, pp.1–4.
- Rouas J-L. Automatic prosodic variations modeling for language and dialect discrimination // IEEE transactions on audio, speech and language processing, 2007, vol.15, no.6, pp.1904–1911.
- Torres-Carrasquillo P. A., Singer E., Kohler М. A. Approaches to language ıdentification using gaussian mixture models and shifted delta cepstral features / Proc. of IEEE ICASSP, 2002, pp.757–760.
- Murty K. S. R., Yegnanarayana B. Epoch extraction from speech signals // IEEE Transactions on Audio, Speech, and Language Processing, 2008, vol.16, no.8, pp.1602–1613.
