Hidden Markov model-based approach for generation of Pitman shorthand language symbols for consonants and vowels from spoken english

@article{citeulike:2801485, abstract = {Abstract\ \ Pitman shorthand language (PSL) is a widely practised medium for transcribing/recording speech to text (StT) in English. This recording medium continues to exist in spite of considerable development in speech processing systems (SPS), because of its ability to record spoken/dictated text at high speeds of more than 120 words per minute. Hence, scope exists for exploiting this potential of PSL in present SPS. In this paper, an approach for feature extraction using Mel frequency cepstral coefficients (MFCC) and classification using hidden Markov models (HMM) for generating strokes comprising consonants and vowels (CV) in the process of production of Pitman shorthand language from spoken English is proposed. The proposed method is tested on a large number of samples, drawn from different speakers and the results are encouraging. The work is useful in total automation of PSL processing.}, author = {Kumar, G. and Ravishankar, M. and Nagabushan, P. and Anami, Basavaraj }, citeulike-article-id = {2801485}, doi = {10.1007/BF02703382}, journal = {Sadhana}, keywords = {pitman\_shorthand}, month = {June}, number = {3}, pages = {277--290}, posted-at = {2008-05-15 13:22:33}, priority = {2}, title = {Hidden Markov model-based approach for generation of Pitman shorthand language symbols for consonants and vowels from spoken english}, url = {http://dx.doi.org/10.1007/BF02703382}, volume = {31}, year = {2006} }

TY - JOUR ID - citeulike:2801485 L3 - citeulike-article-id:2801485 TI - Hidden Markov model-based approach for generation of Pitman shorthand language symbols for consonants and vowels from spoken english JF - Sadhana VL - 31 IS - 3 SP - 277 EP - 290 N2 - Abstract  Pitman shorthand language (PSL) is a widely practised medium for transcribing/recording speech to text (StT) in English. This recording medium continues to exist in spite of considerable development in speech processing systems (SPS), because of its ability to record spoken/dictated text at high speeds of more than 120 words per minute. Hence, scope exists for exploiting this potential of PSL in present SPS. In this paper, an approach for feature extraction using Mel frequency cepstral coefficients (MFCC) and classification using hidden Markov models (HMM) for generating strokes comprising consonants and vowels (CV) in the process of production of Pitman shorthand language from spoken English is proposed. The proposed method is tested on a large number of samples, drawn from different speakers and the results are encouraging. The work is useful in total automation of PSL processing. KW - pitman_shorthand AU - Kumar, G AU - Ravishankar, M AU - Nagabushan, P AU - Anami, Basavaraj PY - 2006/06/18/ UR - http://dx.doi.org/10.1007/BF02703382 ER -