位置：成果数据库 > 期刊 > 期刊详情页
汉语大词汇量连续语音识别系统研究进展
  • 期刊名称：电子学报
  • 时间：0
  • 页码：2000年Vol,28,No.1,P85-91
  • 语言：中文
  • 分类：TP391[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
  • 作者机构：[1]中国科学院自动化研究所模式识别国家重点实验室,北京100190, [2]山东财政学院统计与数理学院,山东济南250014
  • 相关基金：国家重点基础研究发展计划（973）资助项目（2004CB318105）;国家高技术研究发展计划（863）资助项目（2006AA01Z194,20060101Z4073）;国家自然科学基金资助项目（60675026,60121302,90820011）
  • 相关项目：稳健（抗噪）语音识别新方法研究
作者： 刘加|
关键词： 计算机应用, 中文信息处理, 综述, 语音识别, 模型自适应, 搜索技术, computer application, Chinese information processing, overview, speech recognition, model adaptation, search technology
中文摘要：

大词汇量连续语音识别（LVCSR）技术近年来发展迅速，并在许多领域得到了广泛的应用，国内外许多大公司加大了对语音识别技术的研究，不少商业化的语音识别系统已经面世，并得到较为广泛的使用。该文综述了近年来大词汇量连续语音识别技术的研究进展，描述了汉语大词汇量连续语音识别系统，主要是基于统计方法的语音识别系统的框架与设计方法，对语音识别系统的一些关键技术和原理进行了分析，并对近年来国内外对语音识别研究发展动向进行了讨论。

英文摘要：

The technology of large vocabulary continuous speech recognition（LVCSR）has developed quickly and achieved broad application in recent years. Many big companies has reinforced the speech recognition research and various commercial systems have appeared in the market, This paper reviews the recent research progresses of LVCSR and describes the main frames and designs of current mandarin Chinese LVCSR systems. The key issues and principles in LCVSR are analyzed in detail. The prospects and research trends for LVCSR at home and abroad are also discussed.

同期刊论文项目
稳健（抗噪）语音识别新方法研究
期刊论文 12
基于客观质量评估和音频场景分析语音分离新方法研究
期刊论文 36 会议论文 22 获奖 2
基于语音知识和全局最优准则指导的段模型汉语LVCSR方法研究
期刊论文 21 会议论文 25 获奖 2 专利 3
　面向网络应用环境的口语翻译关键技术与系统研究
期刊论文 13
语音、图像与视觉计算
期刊论文 155 会议论文 74 著作 5
同项目期刊论文
Linguistic theory based contextual evidence mining for statistical Chinese co-reference resolution
Efficient Night Gait Recogniti
Motion Detection in driving En
Topology-preserved Diffusion D
Dynamic Similarity Kernel for
Discriminative analysis of ear
Gait Recognition Based on Fusi
Fast global Motion Estimation
基于中间转换格式的中英文语言生
The Parallel Genetic Algorithm
Regional Coherence Changes in
Handedness-Related Functional
Regional Honogeneity Based App
Semantic-based Surveillance Vi
Altered Resting State Function
An Approach to Automatic Acqui
Characterizing The Dynamic Con
Combining Local Features for R
Structure and Motion of Nonrig
A Robust Method toRecognize Cr
Reconstruction of Structured S
Pixon-Based Image Segmentation
Altered Functional Connectivit
Can Image Measurement Errors b
Functional Dysconnectivity of
基于计算听觉场景分析和语者模型信息的语音识别鲁棒前端研究
汉语韵律短语的时长与音高研究
A SVD-Based Watermarking Schem
Esub8: A novel tool to predict
Affine Invariant Classificatio
Catadioptric Camera Calibratio
Alignment of Two Dimensional E
Region Growing Method for the
Global motion Model for stereo
Intensity-Based Robust Similar
A Combinational Feature Select
Silhoutte Analysis based Gait
An Evolutionary Tabu Search fo
A Modified Gabor Filter Design
Brief Review of Invariant Text
A New Easy Camera Calibration
Personal Identification Based
Illumination Invariant Face Re
Visual Vehicle Tracking Algori
A New Constraint on the Imaged
Fingerprint Registration by Ma
Non-rigid Registration of Medi
Quantitative Analysis along th
Exploring Susceptibility Genes
A Co-Chunk based method for Sp
The Impossibility of Affine Re
面向口语翻译的汉语语句改写方法
A hierarchical self-organizing
Single View Metrology from Sce
Volumetric Segmentation of the
Changes in Hippocampal Connect
Functional Disintegration in P
Asymmetry of Prefrontal Cortic
Automatic Gait Recognition bas
Normalization-cooperated gradi
PnP Revisited
Head tracking Using Shape and
Parametric Reconstruction of G
Improving Depth Resolution of
Characterizing Anatomical Diff
Implementation and Experimenta
A Neural Network Approach to S
A?Comparative Study of Global
The Number of Independent Krup
A New Robust Circular Gabor Ba
Modulation of Functional Conne
Toward Practical Spoken Langua
Discriminative Analysis of Rel
The LLE and a Linear Mapping
The Relationship within and be
Side and Handedness Effects on
Dual Cross-Media Relevance Mod
Human Behavior Consistent Rele
A Mid-Level Scene Change Repre
Shape and Texture Based Deform
Image segmentation Using Co-EM
Multiple Similarities Based Ke
Automatic Moving Object Segmen
Semantic Knowledge Extraction
Local Intensity Variation Anal
Efficient Iris Recognition by
Design and Performance Studies
Improving Iris Recognition Acc
Camera Calibration and 3D Reco
Automated Short Proof Generati
Face annotation for family pho
Ensemble-based Discriminant Le
鲁棒的汉语口语解析方法研究
3D Model Base Vehicle Tracking
Recent Developments in Human M
Kernel based Nonlinear Discrim
A Modified Temporal Self-Corre
Asymmetry Analysis of Cingulum
A Real-time Detecting Tracking
Single-Trial Variable Model fo
Do Singular Values Contains Ad
Spontaneous Activity Associate
A Note on the Convergence of t
Camera Calibration with Moving
People Tracking Based on Motio
Hippocampal Shape Analysis of
The Invariant Representations
Protein Folding Simulations of
Multi-context Fuzzy Clustering
Widespread Functional Dysconne
Prosody Conversion from Neutra
A Note on the Number of Soluti
A General Sufficient Condition
A Split-merge Based Region Gro
Whole Brain Functional Connect
Improving Performance of Refle
Learning Multi-View Face Subsp
中文Base NP识别:错误驱动的组合分类器方法
基于“松弛尺度”的短语翻译对抽取方法
阿尔茨海默病脑灰质体积异常的MRI研究
基于MRI海马形状特征的阿尔茨海默病的自动判别
基于Fourier—Mellin变换的图像配准方法及应用拓展
基于三参数模型的快速全局运动估计
基于后验概率解码段模型的汉语语音数字串识别
如何增加人工神经元网络的透明度
基于多统计模型和人耳听觉特性的麦克风阵列后滤波语音增强算法
基于语义分类树的汉语口语理解方法
The Number of Independent Kruppa Constraints from N Images
引入标点处理的层次化汉语长句句法分析方法
应用统计方法综合评估核函数分类能力的研究
椭球基函数神经网络的混合学习算法
采用听觉滤波器的宽带MUSIC声源定位方法
Auditory filter based broadband MUSIC algorithm for sound source localization
基于听觉感知特性的信号子空间麦克风阵列语音增强算法
一种改进的单声道混合语音分离方法
Unsupervised Learning of Gaussian Mixture Model with Application to Image Segmentation
From English pitch accent detection to Mandarin stress detection, where is the difference?
Monaural Voiced Speech Segregation Based on Dynamic Harmonic Function
Monaural speech separation based on MAXVQ and CASA for robust speech recognition
融合引导概率的语音识别解码算法研究
Integrating Induced Probability into Decoding for Large Vocabulary Continuous Speech Recognition
基于计算听觉场景分析和语者模型信息的语音识别鲁棒前端研究
基于互补模型的汉语韵律间断自动检测
基于F范数的信号子空间维度估计的多通道语音增强算法
韵律相关的汉语语音识别系统研究
Mandarin stress detection using acoustic, lexical and syntactic features
基于多空间概率分布的汉语连续语音声调识别研究
改进谐波组织规则的单通道浊语音分离系统
基于韵律间断层级的汉语韵律间断分类
Monaural voiced speech segregation based on elaborate harmonic grouping strategies
基于互补模型的汉语重音检测
基于多统计模型和人耳听觉特性的麦克风阵列后滤波语音增强算法
基于声学相关特征与词典语法相关特征的汉语重音检测
Robust front-end for speech recognition based on computational auditory scene analysis and speaker m
融合引导概率的语音识别解码算法研究
基于计算听觉场景分析和语者模型信息的语音识别鲁棒前端研究
汉语韵律短语的时长与音高研究
A modified monaural mixture speech separation method
基于高斯-拉普拉斯-伽玛模型和人耳听觉掩蔽效应的信号子空间语音增强算法
Perceptual properties based signal subspace microphone array speech enhancement algorithm
基于F范数的信号子空间维度估计的多通道语音增强算法
韵律相关的汉语语音识别系统研究
改进谐波组织规则的单通道浊语音分离系统
基于韵律间断层级的汉语韵律间断分类
基于多基音跟踪的单声道混合语音分离
基于互补模型的汉语重音检测
基于多统计模型和人耳听觉特性的麦克风阵列后滤波语音增强算法
基于声学相关特征与词典语法相关特征的汉语重音检测
GMD-SDDBHMM语音模型和分类算法
基于二次多项式后验概率估计的汉语数码语音识别
用TM320C31实时实现电话语音识别系统
利用多层感知机映射提高不匹配环境下的语音识别性能
Training HMM Using A Minimum Error Critrion with Different Loss Measures
基于电话用户交换机的语音识别系统研究
高性能汉语数码语音识别算法
A Novel Beam Search Algorithm of Speech Recognition for Voice Command Conrtrol
多层前向感知机汉语孤立数码语音识别
利用MCE算法提高说话人识别性能
A New Robust Telephone Speech Recognition Algorithm with the Multi-Model Structures
Integrating Induced Probability into Decoding for Large Vocabulary Continuous Speech Recognition
基于计算听觉场景分析和语者模型信息的语音识别鲁棒前端研究
汉语韵律短语的时长与音高研究
韵律相关的汉语语音识别系统研究
改进谐波组织规则的单通道浊语音分离系统
基于互补模型的汉语重音检测
人机互助的交互式口语翻译方法
基于多模型融合的人名翻译系统
基于混淆网络解码的机器翻译多系统融合