http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Implementation of HMM-Based Speech Recognizer Using TMS320C6711 DSP
Bae Hyojoon,Jung Sungyun,Bae Keunsung The Korean Society Of Phonetic Sciences And Speech 2004 말소리 Vol.52 No.-
This paper focuses on the DSP implementation of an HMM-based speech recognizer that can handle several hundred words of vocabulary size as well as speaker independency. First, we develop an HMM-based speech recognition system on the PC that operates on the frame basis with parallel processing of feature extraction and Viterbi decoding to make the processing delay as small as possible. Many techniques such as linear discriminant analysis, state-based Gaussian selection, and phonetic tied mixture model are employed for reduction of computational burden and memory size. The system is then properly optimized and compiled on the TMS320C6711 DSP for real-time operation. The implemented system uses 486kbytes of memory for data and acoustic models, and 24.5 kbytes for program code. Maximum required time of 29.2 ms for processing a frame of 32 ms of speech validates real-time operation of the implemented system.
TMS320C6711 DSP를 이용한 HMM 기반의 음성인식시스템 구현
배재철(Jaechul Bae),김태환(Taehwan Kim),배건성(Keunsung Bae) 대한전자공학회 2006 대한전자공학회 학술대회 Vol.2006 No.11
In this paper, we implement an HMM-based speech recognizer on the TMS320C6711 DSK. First, we develop an HMM-based speech recognition system on the PC that operates on the frame basis with parallel processing of feature extraction and Viterbi decoding to make the processing delay as small as possible. Many techniques such as linear discriminant analysis, state-based Gaussian selection, and phonetic tied mixture model are employed for reduction of computational burden and memory size. The system is then properly optimized and compiled on the TMS320C6711 DSP for a real-time operation We confirm a real-time operation with the TMS320C6x profiler in Code Composer Studio. And we implement a communication between the host and the TMS320C6711 DSK through the host port interface.
Underwater Transient Signal Classification Using Binary Pattern Image of MFCC and Neural Network
LIM, Taegyun,BAE, Keunsung,HWANG, Chansik,LEE, Hyeonguk The Institute of Electronics, Information and Comm 2008 IEICE transactions on fundamentals of electronics, Vol.91 No.3
<P>This paper presents a new method for classification of underwater transient signals, which employs a binary image pattern of the mel-frequency cepstral coefficients as a feature vector and a feed-forward neural network as a classifier. The feature vector is obtained by taking DCT and 1-bit quantization for the square matrix of the mel-frequency cepstral coefficients that is derived from the frame based cepstral analysis. The classifier is a feed-forward neural network having one hidden layer and one output layer, and a back propagation algorithm is used to update the weighting vector of each layer. Experimental results with underwater transient signals demonstrate that the proposed method is very promising for classification of underwater transient signals.</P>
HMM-Based Underwater Target Classification with Synthesized Active Sonar Signals
KIM, Taehwan,BAE, Keunsung The Institute of Electronics, Information and Comm 2011 IEICE transactions on fundamentals of electronics, Vol.ea94 No.10
<P>This paper deals with underwater target classification using synthesized active sonar signals. Firstly, we synthesized active sonar returns from a 3D highlight model of underwater targets using the ray tracing algorithm. Then, we applied a multiaspect target classification scheme based on a hidden Markov model to classify them. For feature extraction from the synthesized sonar signals, a matching pursuit algorithm was used. The experimental results depending on the number of observations and signal-to-noise ratios are presented with our discussions.</P>
Application of EVRC NS Module to Detection of Underwater Transient Signals
Taehwan Kim,Keunsung Bae 대한전자공학회 2007 ITC-CSCC :International Technical Conference on Ci Vol.2007 No.7
Detection of transient signals is generally done by examining power and spectral variation of the received signal, but it becomes a difficult task when the background noise gets large. In this paper, we make use of the EVRC noise suppression (NS) module for robust detection of underwater transient signals. We define new parameters from the outputs of EVRC NS module for transient detection. Experimental results demonstrate that the proposed method is very promising for detection of underwater transient signals.
Removal Of Noise From Speech Using Wavelet Transform
Jongwon Seok,Keunsung Bae 한국정보과학회 1999 Journal of Electrical Engineering and Information Vol.4 No.3
This paper describes a general problem of removing additive background noise from the noisy speech in the wavelet domain. A semisoft thresholding is used to remove noise components from the wavelet coefficients of noisy speech. To prevent quality degradation of the unvoiced sounds during the denoising process, the unvoiced region is classified first and then thresholding is applied in a different way. For the noisy speech having SNR of 10 to -10 ㏈, the average SNR improvement of 4 to 10 ㏈ is achieved, and experimental results demonstrate that the speech enhancement algorithm using the wavelet transform is very promising.
Detection of Underwater Transient Signals Using EVRC Noise Suppression Module
Taehwan Kim,Keunsung Bae 대한전자공학회 2008 ICEIC:International Conference on Electronics, Inf Vol.1 No.1
Detection of transient signals is generally done by examining power and spectral variation of the received signal, but it becomes a difficult task when the background noise gets large. In this paper, we define a new parameter from the outputs of the EVRC noise suppression module and propose a robust transient detection algorithm using them. Experimental results with various types of underwater transients have shown that the proposed method outperforms the conventional energy-based method and achieved reduction of error rate by 7% ~ 15% for various types of background noise.
Classification of Underwater Transient signals using Binary Pattern Image of MFCC and Neural Network
Taegyun Lim,Keunsung Bae,Chansik Hwang 대한전자공학회 2007 ITC-CSCC :International Technical Conference on Ci Vol.2007 No.7
This paper presents a new method for classification of underwater transient signals, which employs a binary image pattern of the mel-frequency cepstral coefficients as a feature vector and a feed-forward neural network as a classifier. A feature vector is obtained by taking DCT and 1-bit quantization for the square matrix of the mel-frequency cepstral coefficients that is derived from the frame based cepstral analysis. The classifier is a feed-forward neural network having one hidden layer and one output layer, and a back propagation algorithm is used to update the weighting vector of each layer. Experimental results with some underwater transient signals demonstrate that the proposed method is very promising for classification of underwater transient signals.