See this document in CiteSeerX!

A Modular RNN-Based Method for Continuous (2001)  (Make Corrections)  
Mandarin Speech Recognition Yuan-Fu Liao and Sin-Horng Chen, Senior Member,...



  Home/Search   Context   Related

 
View or download:
ntut.edu.tw/~enlab...EEE_March_2001.pdf
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  ntut.edu.tw/~enla...publications1 (more)
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: A new modular recurrent neural network (MRNN)-based method for continuous Mandarin speech recognition (CMSR) is proposed. The MRNN recognizer is composed of four main modules. The first is a sub-MRNN module whose function is to generate discriminant functions for all 412 base-syllables. It accomplishes the task by using four recurrent neural network (RNN) submodules. The second is an RNN module which is designed to detect syllable boundaries for providing timing cues in order to help solve the... (Update)

Active bibliography (related documents):   More   All
3.5:   Modular Recurrent Neural Networks - For Mandarin Syllable   (Correct)
0.6:   An RNN-Based Pre-classification Method for Fast Continuous.. - Sin-Horng Chen   (Correct)
0.5:   Improvements Of The Philips 2000 Taiwan Mandarin - Benchmark System Yuan-Fu   (Correct)

Similar documents based on text:
0.0:   Unknown -   (Correct)

BibTeX entry:   (Update)

@misc{ recognition-modular,
  author = "Mandarin Speech Recognition",
  title = "A Modular RNN-Based Method for Continuous",
  url = "citeseer.ist.psu.edu/749753.html" }
Citations (may not include all citations):
1362   A tutorial on hidden Markov models and selected applications.. (context) - Rabiner - 1989
704   Neural Networks-A Comprehensive Foundation (context) - Haykin - 1994
653   Fundamentals of Speech Recognition (context) - Rabiner, Juang - 1993
644   Finding structure in time - Elman - 1990
472   Hierarchical mixtures of experts and the EM algorithm - Jordan, Jacobs - 1994
193   Connectionist speech recognition -- A hybrid approach (context) - Bourlard, Morgan - 1994
97   An application of recurrent nets to phone probability estima.. - Robinson - 1994
83   Task decomposition through competition in a modular connecti.. - Jacobs, Jordan et al. - 1991
34   Design and evolution of modular neural network architectures - Happel, Murre - 1994
33   The Meta-Pi network: building distributed knowledge represen.. (context) - Waibel - 1992
31   Modularity and scaling in large phonemic neural networks (context) - Waibel, Sawai et al. - 1989
29   Context-dependent classes in a hybrid recurrent network-HMM .. - Kershaw, Robinson et al. - 1996
21   Connectionist Viterbi training: a new hybrid method for cont.. (context) - Franzini, Lee et al. - 1990
15   Continuous speech recognition -- An introduction to the hybr.. (context) - Morgan, Bourlard - 1995
13   Integrating syllable boundary information into speech recogn.. - Wu, Shire et al. - 1997
10   Complete recognition of continuous Mandarin speech for Chine.. (context) - Wang, Ho et al. - 1997
10   Robust parametric modeling of durations in hidden Markov Mod.. (context) - Burshtein - 1996
10   Discriminative training of dynamic programming based speech .. (context) - Chang, Juang - 1993
8   Forward-backward retraining of recurrent neural networks - Senior, Robinson - 1996
7   Statistical and discriminative methods for speech recognitio.. (context) - Juang, Chou et al. - 1996
5   Discriminative analysis of distortion sequences in speech re.. (context) - Chang, Chen et al. - 1993
4   ACID/HNN: Clustering hierarchies of neural networks for cont.. - Fritsch, Finke - 1998
4   Modeling context-dependent phonetic units in a continuous sp.. - Wu, Deng et al. - 1996
3   Isolated-utterance speech recognition using hidden Markov mo.. (context) - Gu, Tseng et al. - 1991
3   An RNN-based preclassification method for fast continuous Ma.. - Chen, Liao et al. - 1998
2   and F. K. Soong, "An N-best candidates-based discriminative .. (context) - Chen - 1994
2   Golden Mandarin (I) --- a real-time Mandarin speech dictatio.. (context) - Lee, Tseng et al. - 1993
2   Context-dependent acoustic models for Chinese speech recogni.. (context) - Ma, Huang et al. - 1996
2   Recognition of Mandarin syllables based on the distribution .. (context) - Wang, Pai - 1993
2   A survey on automatic speech recognition with an illustrativ.. (context) - Lee, Juang - 1996
2   Efficient search using phone probability estimates (context) - Renals, Hochberg - 1995
2   Phonetic modeling in the Philips Chinese continuous-speech r.. (context) - Seide, Wang - 1998
1   Improved syllable-based continuous Mandarin speech recogniti.. (context) - Chang, Chen - 1995
1   Modular recurrent neural networks for Mandarin syllables rec.. (context) - Chen, Liao - 1998
1   Continuous Mandarin speech recognition for Chinese language .. (context) - Shen - 1998
1   Continuous speech recognition with neural networks and stati.. (context) - Gemello, Albesano et al. - 1997
1   Discriminative weighting of HMM statelikelihood using the GP.. (context) - Kwon, Un - 1996
1   for speech recognition, " IEEE Trans. Speech Audio Processin.. (context) - error, methods - 1997

Documents on the same site (http://www.cc.ntut.edu.tw/~enlab07/publications1.htm):
Modular Recurrent Neural Networks - For Mandarin Syllable   (Correct)
Improvements Of The Philips 2000 Taiwan Mandarin - Benchmark System Yuan-Fu   (Correct)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC