Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Automatic Speech Recognition in Mandarin for Embedded Platforms

Fengguang Zhao, Prabhu Raghavan, Sunil K. Gupta, Ziyi Lu, Wentao Gu (1)

Bell Laboratories, Lucent Technologies, New Jersey, USA
(1) Shanghai Jiaotong University, Shanghai, China

In this paper, we describe a real-time automatic speech recognition system for Mandarin for low-cost embedded platforms using fixed-point digital signal processors. The hands-free, speaker-independent speech recognition system employs 41 mono-phone models for representing the sounds in Mandarin Chinese and 11 whole-word models for connected digit recognition. The system achieves greater than 98% recognition accuracy on our hands-free test database of 46 distinct command phrases. The system achieves 95.9% digit accuracy on a 14 speaker, hands-free, connected digit recognition database. The analysis of the results shows that for speakers without dialect, the digit recognition accuracy is almost 98%. We present a detailed analysis of the digit recognition results and propose further improvements. A realtime platform based upon Lucentís DSP1627 fixed-point digital signal processor has been developed.


Full Paper

Bibliographic reference.  Zhao, Fengguang / Raghavan, Prabhu / Gupta, Sunil K. / Lu, Ziyi / Gu, Wentao (2000): "Automatic speech recognition in Mandarin for embedded platforms", In ICSLP-2000, vol.2, 815-818.