Realization of Mandarin continuous digits speech recognition system using Sphinx

Author

Wang, Yun ; Zhang, Xueying

Author_Institution

Coll. of Inf. Eng., Taiyuan Univ. of Technol., Taiyuan, China

Volume

1

fYear

2010

fDate

5-7 May 2010

Firstpage

378

Lastpage

380

Abstract

This paper introduces a speech recognition system of Mandarin continuous digits based on Sphinx. The acoustic model of this system is produced by SphinxTrain, and the language model is acquired from the Cmuclmtk statistical language model. In addition, this system makes use of PocketSphinx recognition engine as a decoder. According to the experiment, the correct rate of this system to a sentence of random length made by speaker-independent is up to 89.58%, and the word correct rate is 97.20%. Therefore, the performance of this system is fairly well.

Keywords

natural language processing; speech recognition; statistical analysis; Cmuclmtk statistical language model; Mandarin continuous digits speech recognition system; PocketSphinx recognition engine; Sphinx; SphinxTrain; speaker-independent; Acoustic applications; Cepstrum; Communication system control; Decoding; Engines; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Natural languages; Speech recognition; Sphinx; acoustic model; language model; speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Communication Control and Automation (3CA), 2010 International Symposium on

Conference_Location

Tainan

Print_ISBN

978-1-4244-5565-2

Type

conf

DOI

10.1109/3CA.2010.5533801

Filename

5533801