检索结果-南通市图书馆

Effective use of the spectral information in speech processing of cochlear implant

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Progress in Natural Science:Materials International 2007年第3期17卷 334-339页

作者： GUAN Tian, GONG Qin and YE Datian ( Joint Research Centre for Biomedical Engineering, Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, China Research Centre of Biomedical Engineering, Graduate School at Shenzhen, Tsinghua University, Shenzhen 518055, China) [a]Joint Research Centre for Biomedical Engineering Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong China [b]Research Centre of Biomedical Engineering Graduate School at Shenzhen Tsinghua University Shenzhen China

Based on the results of the acoustic research on Mandarin, two novel algorithms using the spectral information in speech processing of cochlear implants are purposed and certified effectively by the spectral information of tonal language in acoustic simulation experiments. We bring forward novel algorithms conveying the spectral information based on the choices of the frequency bands. These new algorithms can not only improve the speech recognition ability of cochlear implant users in the noisy environments but also reduce the complexity of computing and the memory occupied, and make it more suitable to be carried out in clinical practice.

关键词： cochlear implant speech signal processing signal processing.

LSB steganalysis of speech data based on distance measure and ML decision

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2007年第3期14卷 103-107页

作者： DENG Zong-yuan SHAO Xi YANG Zhen Institute of signal and Information processing Nanjing University of Postsand Telecommunications Nanjing 210003 China

Steganalysis can be used to classify an object whether or not it contains hidden information. In this article, is presented, a novel approach to detect the presence of least significant bit（LSB） steganographic messages in the voice secure communication system. A distance measure, which has proven to be sensitive to LSB steganography by analysis of variance （ANOVA）, is denoted to estimate the difference between the host signal and the stego signal. Then an maximum likelihood （ML） decision is combined to form the classifier. Statistical experiments show that the proposed approach has a highly accurate rate and low computational complexity.

关键词： speech signal processing LSB steganography steganalysis ML decision

维普期刊数据库

BLIND speech SEPARATION FOR ROBOTS WITH INTELLIGENT HUMAN-MACHINE INTERACTION

在线全文

学校读者我要写书评

暂无评论

Journal of Electronics(China) 2012年第3期29卷 286-293页

作者： Huang Yulei Ding Zhizhong Dai Lirong Chen Xiaoping Department of Communication Engineering Hefei University of Technology Hefei 230000 China Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei 230027 China

speech recognition rate will deteriorate greatly in human-machine interaction when the speaker's speech mixes with a bystander's voice. This paper proposes a time-frequency approach for Blind Source Seperation (BSS) for intelligent Human-Machine Interaction(HMI). Main idea of the algorithm is to simultaneously diagonalize the correlation matrix of the pre-whitened signals at different time delays for every frequency bins in time-frequency domain. The prososed method has two merits: (1) fast convergence speed; (2) high signal to interference ratio of the separated signals. Numerical evaluations are used to compare the performance of the proposed algorithm with two other deconvolution algorithms. An efficient algorithm to resolve permutation ambiguity is also proposed in this paper. The algorithm proposed saves more than 10% of computational time with properly selected parameters and achieves good performances for both simulated convolutive mixtures and real room recorded speeches.

关键词： Blind Source Separation (BSS) Blind deconvolution speech signal processing Human-machine interaction Simultaneous diagonalization

Analysis of Deaf Speakers’ speech signal for Understanding the Acoustic Characteristics by Territory Specific Utterances

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Circuits and Systems 2016年第8期7卷 1709-1721页

作者： Nirmaladevi Jaganathan Bommannaraja Kanagaraj Department of Information Technology Excel Engineering College Namakkal India Department of Electronics and Communication Engineering KPR Institute of Engineering and Technology Coimbatore India

An important concern with the deaf community is inability to hear partially or totally. This may affect the development of language during childhood, which limits their habitual existence. Consequently to facilitate such deaf speakers through certain assistive mechanism, an effort has been taken to understand the acoustic characteristics of deaf speakers by evaluating the territory specific utterances. speech signals are acquired from 32 normal and 32 deaf speakers by uttering ten Indian native Tamil language words. The speech parameters like pitch, formants, signal-to-noise ratio, energy, intensity, jitter and shimmer are analyzed. From the results, it has been observed that the acoustic characteristics of deaf speakers differ significantly and their quantitative measure dominates the normal speakers for the words considered. The study also reveals that the informative part of speech in a normal and deaf speakers may be identified using the acoustic features. In addition, these attributes may be used for differential corrections of deaf speaker’s speech signal and facilitate listeners to understand the conveyed information.

关键词： Deaf Speaker Hard of Hearing Deaf speech processing Assistive Mechanism for Deaf Speaker speech Correction speech signal processing

BLIND speech SEPARATION FOR ROBOTS WITH INTELLIGENT HUMAN-MACHINE INTERACTION

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronics(China) 2012年第Z2期 286-293页

作者： Huang Yulei Ding Zhizhong Dai Lirong* Chen Xiaoping* (Department of Communication Engineering, Hefei University of Technology, Hefei 230009, China) *(Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China)

speech recognition rate will deteriorate greatly in human-machine interaction when the speaker’s speech mixes with a bystander’s voice. This paper proposes a time-frequency approach for Blind Source Seperation (BSS) for intelligent Human-Machine Interaction(HMI). Main idea of the algorithm is to simultaneously diagonalize the correlation matrix of the pre-whitened signals at different time delays for every frequency bins in time-frequency domain. The prososed method has two merits: (1) fast convergence speed; (2) high signal to interference ratio of the separated signals. Numerical evaluations are used to compare the performance of the proposed algorithm with two other deconvolution algorithms. An efficient algorithm to resolve permutation ambiguity is also proposed in this paper. The algorithm proposed saves more than 10% of computational time with properly selected parameters and achieves good performances for both simulated convolutive mixtures and real room recorded speeches.

关键词： Blind Source Separation (BSS) Blind deconvolution speech signal processing Human-machine interaction Simultaneous diagonalization

Roles of computational auditory model in automatic speech recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Progress in Natural Science:Materials International 2000年第12期 9-18页

作者：迟惠生吴玺宏 China Heijing 100871 Peking University Slate Key Laboratory of Machine Perception

The development of computational auditory modeling in the last 30 years is reviewed, and its development in the coming years is predicted.

关键词： computational auditory model speech signal processing automatic speech recognition.

A Real-time Underwater speech Communication System

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

A Real-time Underwater Speech Communication System

Adaptive Wavelet Packet Filter-Bank Based Acoustic Feature for speech Emotion Recognition

2012年计算机应用与系统建模国际会议

作者： Jiang Jingsai Ma Xiaofeng Li Ye Fan Yanhong Hao Qiuyun Shandong Computer Science Center Shandong Provincial Key Laboratory of computer Network

With frequency hopping (FH) communication system and ultra-low-rate speech coding technology, the paper designed a real-time underwater speech communication system, for which the hardware solution is also given. In the system, the part of source coding is a 300bps vocoder based on enhanced mixed excitation linear prediction (MELPE). In order to overcome the multi-path interference in underwater acoustic communication, FH technology is used because of its low probability of intercept as well as anti-interference. The test results showed that the system had good performance and could be used for underwater communication.

关键词： speech signal processing MELPE BPVC LSF FH 4FSK

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Adaptive Wavelet Packet Filter-Bank Based Acoustic Feature f...