Special speech recognition approaches for the highly confusing Mandarin syllables based on hidden Markov models

Lee, Lin-Shan; Tseng, Chiu‐yu; Liu, Fuhua; Chang, Robert Chen-Hao; Gu, Hung-Yan; Hsieh, Shu‐Kai; Chen, C.H.

doi:10.1016/0885-2308(91)90024-k

Cited by 10 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some works have also been reported on Asian tone languages such as Mandarin [6,14,16,19,23,31,32] Cantonese [15,21,22,25,63] and Thai [39,59]. Ray and Ghoshal [26] have also reported the development an ASR for vowels of three Indian languages, namely: Telugu, Assamese and Bengali and Salor et al [60] have reported works on Turkish.…”

Section: Introductionmentioning

confidence: 91%

See 1 more Smart Citation

Automatic recognition of oral vowels in tone language: Experiments with fuzzy logic and neural network models

íkínbí

Odéjobí

2011

Applied Soft Computing

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 91%

“…F0 = 176.03 Hz satisfy the requirement of Eq. (14) only and produce H (f0) = 1.00. This implies that F0 is HIGH.…”

Section: Fuzzy Inference Enginementioning

confidence: 97%

Automatic recognition of oral vowels in tone language: Experiments with fuzzy logic and neural network models

íkínbí

Odéjobí

2011

Applied Soft Computing

View full text Add to dashboard Cite

“…Hence, Eq2 just involves simple additive and multiplicative operations and avoids complex exponential, logarithmic and division operations. Consequently, the computation of observation probabilities can be simplified with little loss in recognition accuracy [6,7]. We will discuss the details in the section of experimental results.…”

Section: Simplifying the Computation Of Observationmentioning

confidence: 99%

Efficient decoding algorithms for Mandarin connected digit speech recognition

Zhu

Li²,

Jia³

et al.

Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01

View full text Add to dashboard Cite

In this paper, a set of efficient decoding algorithms based on a Speaker Independent Mandarin Connected Digit Speech Recognition System is proposed. By simplifylng the computation of observation probabilities and adopting improved beam search pruning algorithm combined with duration information, the average decoding time is reduced from 0.92 second to 0.1 1 second per digit string while the recognition rate of unknown-length string is only decreased from 94.3% to 94.0%.

show abstract

A simple statistical speech recognition of mandarin monosyllables

Chang

Lee

2006

Applied Mathematics and Computation

View full text Add to dashboard Cite

Special speech recognition approaches for the highly confusing Mandarin syllables based on hidden Markov models

Cited by 10 publications

References 17 publications

Automatic recognition of oral vowels in tone language: Experiments with fuzzy logic and neural network models

Automatic recognition of oral vowels in tone language: Experiments with fuzzy logic and neural network models

Efficient decoding algorithms for Mandarin connected digit speech recognition

A simple statistical speech recognition of mandarin monosyllables

Contact Info

Product

Resources

About