Loading [MathJax]/extensions/MathZoom.js
Huisheng Chi - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Huisheng Chi

Publications
17
Citations
51
Publications by Year
19922009
Co-Authors:
Show All Co-Authors (20)
Image of author Huisheng Chi

Huisheng Chi

Affiliation

Hearing Research Center
Key Laboratory of Machine Perception ( Ministry of Education )
Peking University, Beijing, China

Publication Topics

Biography

Huisheng Chi (M'81–SM'88) received the B.Sc. degree from the Department of Radioelectronics, Peking University, China, in 1964.,He joined the Department of Radioelectronics, Peking University, as an Assistant in 1964. In 1972, he led the University's research efforts in developing a satellite communications system that utilized Spread Spectrum technology. He began researching the use of an Optical Fiber system with regards to telephone traffic, the first-ever application of this type of technology in China. Then, from 1983 to 1990, he worked on a large-scale research project that involved both Intelligent VSAT and TDM/CDMAA technology. In 1986, he joined the Chinese National Laboratory on Machine Perception as a Deputy Director and then as ...
Publications
17
Citations
51
Publications by Year
19922009
Co-Authors:
Show All Co-Authors (20)
Author's Published Works

Showing 1-17 of 17 results

  • Sort

Filter Results

Show

Sort By

Results

PHMM based asynchronous acoustic model for Chinese large vocabulary continuous speech recognition

Hao Wu;Xihong Wu;Huisheng Chi

2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2009 | Conference Paper |
In this paper, we presented an asynchronous multiple stream based Chinese tonal acoustic modeling framework. In this framework, toneless phonetic units and tones are modeled separately with different acoustic features. During the training and decoding process, a set of models are coupled together with a product hidden Markov models (PHMM) to represent whole tonal phonetic units. Through this, a co...Show More

PHMM based asynchronous acoustic model for Chinese large vocabulary continuous speech recognition

Hao Wu;Xihong Wu;Huisheng Chi

Year: 2009 | Conference Paper |

Outliers Learning and Its Applications

Dingsheng Luo;Xinhao Wang;Xihong Wu;Huisheng Chi

2005 International Conference on Neural Networks and Brain
Year: 2005 | Conference Paper |
Cited by: Papers (1)
Outlier problem is one of the typical problems in an incomplete data based machine learning system [1][2][3]. An outlier is a pattern that was either mislabeled in the training data, or inherently ambiguous and hard to recognize, therefore, it usually brings extra trouble for a learning task, either in debasing the performance or leading the learning process to be more complicated. In order to tac...Show More

Outliers Learning and Its Applications

Dingsheng Luo;Xinhao Wang;Xihong Wu;Huisheng Chi

Year: 2005 | Volume: 2 | Conference Paper |

Improving Chinese text categorization by outlier learning

Xinhao Wang;Dingsheng Luo;Xihong Wu;Huisheng Chi

2005 International Conference on Natural Language Processing and Knowledge Engineering
Year: 2005 | Conference Paper |
Cited by: Papers (2) | Patents (1)
Text categorization is one of the typical machine learning tasks that suffer from an incomplete training data problem. A main reason is the existence of outliers in training data, such as non-sense documents, documents mislabeled or lying on the border between different categories, and documents that are out of the defined categories, etc. Therefore, in a text categorization task, outlier learning...Show More

Improving Chinese text categorization by outlier learning

Xinhao Wang;Dingsheng Luo;Xihong Wu;Huisheng Chi

Year: 2005 | Conference Paper |

Learning effective features for Chinese text categorization

Dingsheng Luo;Xinhao Wang;Xihong Wu;Huisheng Chi

2005 International Conference on Natural Language Processing and Knowledge Engineering
Year: 2005 | Conference Paper |
Text categorization task always suffers from a high dimension problem, which leads the learning system to be in a status of either lower efficiency or lower performance. A number of feature selection methods have therefore been adopted or proposed for its dimensional reduction, such as DF, IG, Chi Square and so on. Unlike those traditional feature selection methods, in this paper, a feature select...Show More

Learning effective features for Chinese text categorization

Dingsheng Luo;Xinhao Wang;Xihong Wu;Huisheng Chi

Year: 2005 | Conference Paper |

Biomimetics speaker identification systems for network security gatekeepers

Xihong Wu;Dingsheng Luo;Huisheng Chi;H. Szu

Proceedings of the International Joint Conference on Neural Networks, 2003.
Year: 2003 | Conference Paper |
The perception mechanisms of the human auditory periphery and cochlear nucleus were simulated and the potential application to the voice password gatekeeper was discussed. A biomimetics speaker identification system was implemented based on the auditory processing. Obvious improvement in the robustness was shown under a noisy environment.Show More

Biomimetics speaker identification systems for network security gatekeepers

Xihong Wu;Dingsheng Luo;Huisheng Chi;H. Szu

Year: 2003 | Volume: 4 | Conference Paper |

Capture interspeaker information with a neural network for speaker identification

Lan Wang;Ke Chen;Huisheng Chi

IEEE Transactions on Neural Networks
Year: 2002 | Volume: 13, Issue: 2 | Journal Article |
Cited by: Papers (13)
Model-based approach is one of methods widely used for speaker identification, where a statistical model is used to characterize a specific speaker's voice but no interspeaker information is involved in its parameter estimation. It is observed that interspeaker information is very helpful in discriminating between different speakers. In this paper, we propose a novel method for the use of interspe...Show More

Capture interspeaker information with a neural network for speaker identification

Lan Wang;Ke Chen;Huisheng Chi

Year: 2002 | Volume: 13, Issue: 2 | Journal Article |

Capture inter-speaker information with a neural network for speaker identification

Lan Wang;Ke Chen;Huisheng Chi

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium
Year: 2000 | Conference Paper |
Cited by: Papers (1)
Many speaker identification systems are created by model-based approaches, where a statistical model is used to characterize a speaker's voice and no inter-speaker information is used in parameter estimation. It is well known that inter-speaker information is very helpful in discrimination of different speakers. We propose a method for the use of inter-speaker information to improve performance of...Show More

Capture inter-speaker information with a neural network for speaker identification

Lan Wang;Ke Chen;Huisheng Chi

Year: 2000 | Volume: 5 | Conference Paper |

On use of different feature sets for pattern classification: an alternative method

Ke Chen;Huisheng Chi

IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)
Year: 1999 | Conference Paper |
Cited by: Papers (1)
We propose an alternative method for the use of different feature sets in pattern classification. Unlike traditional methods, e.g. combination of multiple classifiers and use of a composite feature set, our method copes with the problem based on an idea of soft competition on different feature sets, a modular neural network architecture is proposed to implement the idea accordingly. The proposed a...Show More

On use of different feature sets for pattern classification: an alternative method

Ke Chen;Huisheng Chi

Year: 1999 | Volume: 5 | Conference Paper |

Auditory model based speech feature extraction and its application to speaker identification

Bing Xiang;Xihong Wu;Zhimin Liu;Huisheng Chi

IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)
Year: 1999 | Conference Paper |
According to the characteristics of the auditory periphery and cochlear nucleus, as well as attempting to simulate the mechanism of auditory system as a whole, two kinds of novel speech feature are presented in this paper, and a framework of neural network has been adopted. The two features considered are: the weighted average localized synchronized rate cepstrum, and the weighted firing rate ceps...Show More

Auditory model based speech feature extraction and its application to speaker identification

Bing Xiang;Xihong Wu;Zhimin Liu;Huisheng Chi

Year: 1999 | Volume: 1 | Conference Paper |

An HMM/MFNN hybrid architecture based on stacked generalization for speaker identification

Weiquan Bao;Ke Chen;Huisheng Chi

1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227)
Year: 1998 | Conference Paper |
Cited by: Papers (1)
A hybrid architecture based upon hidden Markov models (HMMs) and multilayer feedforward neural network (MFNN) is presented for speaker identification. Unlike most of the previous combing methods, the proposed architecture uses HMMs to model individual speaker and uses MFNN to deal with the inter-speaker information for improving performance. Learning in the proposed architecture consists of two ph...Show More

An HMM/MFNN hybrid architecture based on stacked generalization for speaker identification

Weiquan Bao;Ke Chen;Huisheng Chi

Year: 1998 | Volume: 1 | Conference Paper |

A modified mixtures of experts architecture for classification with diverse features

Ke Chen;Huisheng Chi

Proceedings of International Conference on Neural Networks (ICNN'97)
Year: 1997 | Conference Paper |
Cited by: Papers (1) | Patents (1)
A modular neural architecture, MME, is considered here as an alternative to the standard mixtures of experts architecture for classification with diverse features. Unlike the standard mixtures of experts architecture, a gate-bank consisting of multiple gating networks is introduced to the proposed architecture, and those gating networks in the gate-bank receive different input vectors while expert...Show More

A modified mixtures of experts architecture for classification with diverse features

Ke Chen;Huisheng Chi

Year: 1997 | Volume: 1 | Conference Paper |

Detection of spectral transition for speech perception based on time-frequency analysis

Qun Zhao;Qianli Gao;Huisheng Chi

Proceedings of ICICS, 1997 International Conference on Information, Communications and Signal Processing. Theme: Trends in Information Systems Engineering and Wireless Multimedia Communications (Cat.
Year: 1997 | Conference Paper |
Cited by: Papers (1)
Current speech or speaker recognition systems rely largely on voiced parts of utterance, though a great amount of information for speech perception is contained in the nonstationary consonants and transition. How to model and characterize the dynamic spectral features describing the transition still remains a question. This paper investigates the modeling and detection of the spectral transition b...Show More

Detection of spectral transition for speech perception based on time-frequency analysis

Qun Zhao;Qianli Gao;Huisheng Chi

Year: 1997 | Volume: 1 | Conference Paper |

Combine multiple time-delay HMEs for speaker identification

Ke Chen;Dahong Xie;Huisheng Chi

Proceedings of International Conference on Neural Networks (ICNN'96)
Year: 1996 | Conference Paper |
Cited by: Papers (1)
In this paper, we present a scheme of combining multiple time-delay nets with the structure of the hierarchical mixture of experts (HME) in order to complete a multi-scale analysis for the temporal data. This method extends the technique of combining multiple classifiers based upon the same static input to sequence processing. We have already applied the proposed method to a real-world problem, ca...Show More

Combine multiple time-delay HMEs for speaker identification

Ke Chen;Dahong Xie;Huisheng Chi

Year: 1996 | Volume: 4 | Conference Paper |

A modified HME architecture for text-dependent speaker identification

Ke Chen;Dahong Xie;Huisheng Chi

IEEE Transactions on Neural Networks
Year: 1996 | Volume: 7, Issue: 5 | Journal Article |
A modified hierarchical mixtures of experts (HME) architecture is presented for text-dependent speaker identification. A new gating network is introduced to the original HME architecture for the use of instantaneous and transitional spectral information in text-dependent speaker identification. The statistical model underlying the proposed architecture is presented and learning is treated as a max...Show More

A modified HME architecture for text-dependent speaker identification

Ke Chen;Dahong Xie;Huisheng Chi

Year: 1996 | Volume: 7, Issue: 5 | Journal Article |

Speaker identification based on the time-delay hierarchical mixture of experts

Ke Chen;Dahong Xie;Huisheng Chi

Proceedings of ICNN'95 - International Conference on Neural Networks
Year: 1995 | Conference Paper |
Cited by: Papers (6)
In this paper, we explore the hierarchical mixture of experts (HME) architecture for a substantial problem, that of text-dependent speaker identification. For a specific multiway classification, we propose a generalized Bernolli density instead of the multinomial logit density. Time-delay technique is also introduced to HME for spatio-temporal processing. Using the proposed density and the time-de...Show More

Speaker identification based on the time-delay hierarchical mixture of experts

Ke Chen;Dahong Xie;Huisheng Chi

Year: 1995 | Volume: 4 | Conference Paper |

A TDM/CDMA VSAT network integrating voice/data service and its operation management

Haige Xiang;Xinping Guo;Qinglin Liang;Yaohuang Yu;Xuqiang Liao;Shouren Wang;Yie Jin;Huisheng Chi

[Proceedings] Singapore ICCS/ISITA `92
Year: 1992 | Conference Paper |
Cited by: Papers (1) | Patents (6)
A TDM/CDMA VSAT network is described in which the data and real-time vocoder service can be simultaneously provided. The network architecture, link design, switching equipment, communication protocol and network management etc. are given.<>Show More

A TDM/CDMA VSAT network integrating voice/data service and its operation management

Haige Xiang;Xinping Guo;Qinglin Liang;Yaohuang Yu;Xuqiang Liao;Shouren Wang;Yie Jin;Huisheng Chi

Year: 1992 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.