Total views : 99
An Analysis of Automatic Phone Recognition and Identification of a Few Languages from North Eastern India
Objective: Phones are basic sound units available in the spoken data. Languages differ among themselves due to use of different phone sets. This paper analyzes some aspects of automatic phone recognition and subsequent identification of a few languages from North Eastern region of India using Phonetic Engine (PE). Methods and Statistical Analysis: PE is a system which converts a speech sample into some symbolic form so that these symbols are capable of capturing all the information carried by the speech sample. In the development of PEs, the International Phonetic Alphabet (IPA) symbols are used in the data transcription process. In modelling the phonetic units Hidden Markov Models (HMM) have been used in the training phase. These trained HMMs are then used in phone recognitions leading to the identification of language(s) of unknown test utterances. Findings: PEs are built for three Indian Languages and one dialect, namely Manipuri, Assamese and Bengali and the Kakching dialect of Manipuri. These languages are widely spoken across the North Eastern region of India. The overall phone recognition accuracies reported by the PEs for the above selected languages are 62:11% for standard Manipuri language, 59:0% for Kakching dialect of Manipuri, 43:28% for standard Assamese and 48:58% for Bengali language. Application: Automatic LID is possible using a set of PEs in testing unknown utterances due to the language bias of these systems. Various level of identification rates reported in some LID tasks carried out with PEs are discussed here to make an analysis of the issues belonging to it.
Hidden Markov Models (HMM), International Phonetic Alphabet (IPA), Language Dependency, Language Identification (LID), Phone Recognition, Phonetic Engine (PE).
- Eswar P. A rule-based approach for spotting characters from continuous speech in Indian languages [Ph.D. thesis]. IIT Madras: 1990.
- Gangashetty SV. Neural network model for recognition of consonent-vowel units in multiple languages [Ph.D. thesis]. IIT Madras: 2004.
- Yegnanarayana B, Gangashetty SV, Rajendran S, Murty KSR, Dhananjaya N, Guruprasad S. A Phonetic Engine for Indian languages. 7th International Conference on Natural Language Processing (ICON-2009); Hyderabad, India. 2009, pp. 8391.
- Sarma BD, Sarma M, Prasanna SRM. Development of Assamese Phonetic Engine: some issues. IEEE India Conference (INDICON-2013); Mumbai, India. 2013, pp. 1-6. Crossref
- Yegnanarayana B, Gangashetty SV. Machine learning for speech recognition-an illustartion of phonetic engine using Hidden Markov Models. International Conference on Frontiers of Interface between Statistics and Sciences, Hyderabad: 2009. PMid:19813815
- International Phonetic Association. Handbook of International Phonetic Association. UK: Cambridge University Press; 1999.
- Dutta SK, Salam NK, Singh LJ. Development of Manipuri Phonetic Engine and its application in language identification. International Journal of Engineering and Technical Research. 2015; 3(8):200–3.
- Schwarz P. Phone Recognition based on long temporal context [Ph.D. thesis]. Faculty of Information technology, Bruno University of Technology; 2008.
- Nagesh A, Sadanadam M. Language identification using Ergodic Hidden Markov Model. International Journal of Advanced research in Computer Science and software Engineering. 2012; 2(11):297–301.
- Young S. HTK book. Cambridge, UK: Cambridge University Engineering Department; 2005.
- Dutta SK, Salam NK, Singh LJ. Development of language identification system using Phonetic Engine. International Conference on Computing and Communication Systems (I3CS'15); Shillong: 2015.
- Huang X, Accero A, Hon HW. Spoken language processing: A guide to theory algorithm and system development. USA: Prentice Hall; 2001. p. 1008.
- Rong T. Automatic speaker and language identification [Ph.D. thesis] Singapore: Nayang Technical University; 2006.
- Rabiner L, Juang B. Fundamentals of speech processing. USA: Prentice Hall; 1993. p. 1–3.
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.