Title :
Hierarchical phoneme classifier for Hindi speech
Author :
Singhvi, Abhinav ; Gupta, Prashant ; Sanyal, Sudip
Author_Institution :
IIT Allahabad, Allahabad
Abstract :
In this work we develop a phoneme segmentation and phoneme recognition for Hindi speech recognition. Novel features like the number of dominating frequencies, the primary and secondary dominating frequencies are used in addition to standard features like zero crossing, length of the phoneme and energy. The results obtained with standard data sets show that the system has an accuracy of more than 85%.
Keywords :
natural language processing; speech recognition; Hindi speech recognition; hierarchical phoneme classifier; phoneme recognition; phoneme segmentation; Classification tree analysis; Computer vision; Decision trees; Frequency; Hidden Markov models; Natural languages; Sampling methods; Signal processing; Speech recognition; Tongue;
Conference_Titel :
Signal Processing, 2008. ICSP 2008. 9th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-2178-7
Electronic_ISBN :
978-1-4244-2179-4
DOI :
10.1109/ICOSP.2008.4697197
