Hybrid Networks of Neural Nets and Hidden Markov Models Applied to Speech Recognition

Li Weiying; Yi Kechu; Hu Zheng

您当前的位置：

首页 >

文章列表页 >

Hybrid Networks of Neural Nets and Hidden Markov Models Applied to Speech Recognition

更新时间：2025-12-08

- Hybrid Networks of Neural Nets and Hidden Markov Models Applied to Speech Recognition
- Acta Electronica Sinica Issue 10, (1994)
- 作者机构：
  
  西安电子科技大学信息工程系
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.34
- Published：1994
- 稿件说明：
移动端阅览
[1]李苇营,易克初,胡征.神经网络与HMM构成的混合网络在语音识别中应用的研究[J].电子学报,1994(10):73-80.

Li Weiying, Yi Kechu, Hu Zheng. Hybrid Networks of Neural Nets and Hidden Markov Models Applied to Speech Recognition[J]. Acta Electronica Sinica, 1994, (10).
[1]李苇营,易克初,胡征.神经网络与HMM构成的混合网络在语音识别中应用的研究[J].电子学报,1994(10):73-80. DOI：

Li Weiying, Yi Kechu, Hu Zheng. Hybrid Networks of Neural Nets and Hidden Markov Models Applied to Speech Recognition[J]. Acta Electronica Sinica, 1994, (10). DOI：

摘要

隐马尔可夫模型（ＨＭＭ）技术是语音识别中应用较为成功的算法，但它的缺点影响了其精度、速度、硬件实现和推广应用，神经网络（ＮＮ）具有并行性、强的分类能力和易于硬件实现等优点。将ＮＮ与ＨＭＭ相结合构成混合网络，能克服ＨＭＭ与ＮＮ的缺点，保留双方的优点，本文详细评述了目前在语音识别中应用的由ＨＭＭ和ＮＮ构成的四种混合网络。通过对其结构、识别性能和特点的分析，可以看出ＨＭＭ和ＮＮ构成的混合网的性能明显优于纯ＨＭＭ和ＮＮ，是更适于语音识别的网络。

Abstract

Hidden Markov Model（HMM）is a successfully used algorithm in speech recognition

yet its disadvantages limit its performance

speed

hardware implementation and application. Neural network （NN）has many advantages such as parallel processing ability

powerful discriminating ability

ease of hardware implementation etc.The hybrid systems based on the combination of HMM and NN can overcome their disadvantages while maintain their advantages.In this paper

four kinds of HMM and NN hybrid systems which have been widely used in speech recognition were described in detail. From the discussion of their structure

recognition performance and characteristics

it can be seen that the gybrid systems are superior to HMM and NN thus are more suitable for speech recognition.

关键词

Keywords

references

Views

445

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hardware Realization of Semiconductor Neurocomputer and Its Application to Continuous Speech Recognition

Coarse Classification Based on KL Discreminant Information for Speech Recognition

Chinese Speech Recognition Based on Finite-State Radial Basis Function Networks

Real-Time Gesture Recognition Algorithm Based on LoRa Signals

Continual Learning Methods and Applications in Computer Vision

Related Author

WANG Shou-jue

CAO Wen-ming

Zhan Puming

Lu Dajin & Wang Zuoying

王作英

李苇营

易克初

吴文虎

Related Institution

Lab of Artificial Neural Networks,Institute of Semiconductors,CAS

School of Information,Zhejiang University of Technology

Lab of Artificial Neural NetworksInstitute of SemiconductorsCASBeijing 100083China

School of InformationZhejiang University of TechnologyHangzhouZhejiang 310014China

Dept. of Electronic Engineering, Tsinghua University

⁰