Title :
Speech recognition using neural networks
Author :
Khan, Shafi Ullah ; Sharma, Govind ; Rao, P.R.K.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., Kanpur, India
Abstract :
The paper presents a continuous speech recognition system based on a neural network concept. An articulatory-phonetic feature extraction network (APFEN) is used for extracting articulatory-phonetic features. This is followed by a coarticulation network for reducing the effect of coarticulation present in the continuous speech. Algorithms for segmentation and then identification of phonemes are given.
Keywords :
feature extraction; identification; neural nets; speech recognition; articulatory-phonetic feature extraction network; coarticulation network; continuous speech coarticulation; continuous speech recognition system; neural network concept; neural networks; phenome identification algorithm; phenome segmentation algorithm; speech recognition; Cepstrum; Feature extraction; Frequency domain analysis; Humans; Linear predictive coding; Mel frequency cepstral coefficient; Neural networks; Paper technology; Reflection; Speech recognition;
Conference_Titel :
Industrial Technology 2000. Proceedings of IEEE International Conference on
Print_ISBN :
0-7803-5812-0
DOI :
10.1109/ICIT.2000.854165
