DocumentCode :
2418203
Title :
Continuous digit recognition in mobile environment
Author :
Kafley, Sabin ; Vuppala, Anil Kumar ; Chauhan, Arun ; Rao, K. Sreenivasa
Author_Institution :
Sch. of Inf. Technol., Indian Inst. of Technol. Kharagpur, Kharagpur, India
fYear :
2010
fDate :
3-4 April 2010
Firstpage :
217
Lastpage :
222
Abstract :
This paper deals with the recognition of digits uttered in continuous manner in mobile environment (i.e uttering a telephonic data like phone number). In mobile environment, the major issues are background noise, coding and channel impairments. Most of the existing works deal only with the recognition of noisy speech, but in this paper, we have explored about the recognition of speech under noisy coded condition, and it is shown that the performance of recognition is improved by spectral processing techniques. Finally, in this paper, we have shown that speech coding does not significantly affect on the performance of digit recognition. Also, we have compared the results of spectral methods used here for preprocessing, and concluded that Minimum Mean Square Error (MMSE) method produces better result than spectral subtraction method.
Keywords :
mean square error methods; speech coding; speech recognition; background noise; channel impairment; coding impairment; continuous digit recognition; minimum mean square error method; mobile environment; noisy coded condition; noisy speech recognition; spectral processing; spectral subtraction method; speech coding; Acoustic noise; Background noise; Degradation; Frequency; Paper technology; Speech analysis; Speech enhancement; Speech processing; Speech recognition; Working environment noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Students' Technology Symposium (TechSym), 2010 IEEE
Conference_Location :
Kharagpur
Print_ISBN :
978-1-4244-5975-9
Electronic_ISBN :
978-1-4244-5974-2
Type :
conf
DOI :
10.1109/TECHSYM.2010.5469151
Filename :
5469151
Link To Document :
بازگشت