• 전기전자학회논문지
• /
• 제17권3호
• /
• pp.241-247
• /
• 2013

This paper presents the design of a System on Programmable Chip (SoPC) based on Field Programmable Gate Array (FPGA) for speech recognition in which Mel-Frequency Cepstral Coefficients (MFCC) for speech feature extraction and Vector Quantization for recognition are used. The implementing process of the speech recognition system undergoes the following steps: feature extraction, training codebook, recognition. In the first step of feature extraction, the input voice data will be transformed into spectral components and extracted to get the main features by using MFCC algorithm. In the recognition step, the obtained spectral features from the first step will be processed and compared with the trained components. The Vector Quantization (VQ) is applied in this step. In our experiment, Altera's DE2 board with Cyclone II FPGA is used to implement the recognition system which can recognize 64 words. The execution speed of the blocks in the speech recognition system is surveyed by calculating the number of clock cycles while executing each block. The recognition accuracies are also measured in different parameters of the system. These results in execution speed and recognition accuracy could help the designer to choose the best configurations in speech recognition on SoPC.

• 한국음향학회지
• /
• 제8권5호
• /
• pp.102-112
• /
• 1989

본 논문은 불특정 화자의 DDD 지역명 인식 실험에 관한 것으로 VQ(Vector Quantization) 방식을 이용하여 실험하였고 인식대상 어휘로는 다이얼링 시스템의 응용을 목적으로 전국 146재의 DDD 지역명을 선정하였다. 특징 파라메타로는 12차 LPC Cepstrum 계수를 사용하여 코우드북을 작성하였으며, 중심점을 찾는 방법으로는 MINSUM 방법과 MINIMAX 방법을 사용하였고 코우드북 작성에는 Splitting rule 3가지를 사용하였다. 코우드북도 Single Section 코우드북과 시간정보를 포함하는 Multi Section 코우드북으로 나누어 작성하였고 Section을 Overlapping 하여가면서 코우드북을 작성하여 실험하였다. 실험 결과 minsum 방법이 minimax 보다 인식률이 좋은 것으로 나타났으며 화자 독립의 경우 약 $90\%$의 인식율을 얻을 수 있었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.54-57
• /
• 2000

In vector quantization (VQ), mean squared difference (MSD) is a widely used distance measure between vectors. But the distance between the means of each vector elements appears as a dominant quantity in MSD. In the case of image vectors, the coincidence of edge patterns is also important when the human visual system (HVS) is considered. Therefore, we propose a new distance measure that uses the variance of differences to encode vectors and to design codebooks. It can choose more proper codewords to reduce edge degradations and make a useful codebook, which has lots of various edge codewords in place of redundant shades.

• KIEE International Transaction on Systems and Control
• /
• 제12D권1호
• /
• pp.7-11
• /
• 2002

In this study, fur the shape-based image retrieval, a method using local differential invariants is proposed. This method calculates the differential invariant feature vector at every feature point extracted by Harris comer point detector. Then through vector quantization using LBG algorithm, all feature vectors are represented by a codebook index. All images are indexed by the histogram of codebook index, and by comparing the histograms the similarity between images is obtained. The proposed method is compared with the existing method by performing experiments for image database including various 1100 trademarks.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.448-455
• /
• 1996

In this paper, we have proposed a VQ algorithm which uses a generating order to make quantize feature vector of speech signal. The proposed algorithm inspects what codeword follows a(ter present codeword and adds new index to established codebook, when mapping speech signal. We present a variable bit rate for new codebook, and propose an efficient compressed way of information. In this way, the number of computation and the number of codewords to be searched are reduced considerably. The performance of the proposed VQ algorithm is evaluated by spectrum distortion measure and bit rate. The obtained spectrum distortion is reduced about 0.22 [db], and the bit rate is saved over 0.21 bit/frame.

• The Journal of the Acoustical Society of Korea
• /
• 제14권1E호
• /
• pp.46-55
• /
• 1995

본 논문에서는 대역선택 웨이브릿 변환 CELP 보호화기라 명명한 4.8 kbps 전송률의 새로운 웨이브릿 변화형 CELP 부호화기를 구현하였다. 제안된 알고리듬에서는 이산 웨이브릿 주파수 대역에 대한 대역 선택과 선택적 벡터 양자화 기법을 사용하였다. 이러한 대역 선택 및 선택적 벡터 양자화 구조는 구분형 VQ 구조를 이용하여 구현하였다. 제안한 알고리즘은 계산량 및 저장용량을 크게 줄이면서도, 기존의 불규칙 잡음 코드북 검색 구조에 비해 0.5에서 1 dB 가량 개선된 segmental SNR을 갖는다. 많은 실험 결과를 통해 확인한 결과, 제안된 대역 선택 웨이브릿 변환 CELP 부호화기는 기존의 CELP 구조나 웨이브릿 변환 구조에 비해서 실제 응용에 훨씬 적합함을 확인하였다.

• 한국통신학회논문지
• /
• 제30권9C호
• /
• pp.877-886
• /
• 2005

Various frame recovery algorithms have been suggested to overcome the communication quality degradation problem due to Internet-typical impairments on Voice over IP(VoIP) communications. In this paper, we propose a new receiver-based recovery method which is able to enhance recovered speech quality with almost free computational cost and without an additional increment of delay and bandwidth consumption. Most conventional recovery algorithms try to recover the lost or erroneous speech frames by reconstructing missing coefficients or speech signal during speech decoding process. Thus they eventually need to modify the decoder software. The proposed frame recovery algorithm tries to reconstruct the missing frame itself, and does not require the computational burden of modifying the decoder. In the proposed scheme, the Vector Quantization(VQ) codebook indices of the erased frame are directly estimated by referring the pre-computed VQ Codebook Index Interpolation Tables(VCIIT) using the VQ indices from the adjacent(previous and next) frames. We applied the proposed scheme to the ITU-T G.723.1 speech coder and found that it improved reconstructed speech quality and outperforms conventional G.723.1 loss recovery algorithm. Moreover, the suggested simple scheme can be easily applicable to practical VoIP systems because it requires a very small amount of additional computational cost and memory space.

• 한국정보처리학회논문지
• /
• 제3권5호
• /
• pp.1307-1316
• /
• 1996

본 논문에서는 인접블록들간의 높은 상관성을 이용한 동적 주소 사상에 의한 벡터 양자화 방법을 제안했다. 제안한 방법에서는 부호화할 입력블록에 대한 벡터 양자화의 주소를 사이드 메치 오차를 이용하여 재정렬된 부호책에서의 새로운 주소로 사상하는 주소 변환 함수를 저의하여 비트율을 효율적으로 감소하였다. 이러한 방법은 주소 변환 함수에 의한 새로운 주소가 주소 문턱값 이하인 낮은 주소로 사상된 경우에는 새롭게 사상된 주소를 부호화하고, 그렇지 않은 경우에는 재정립 되지않은 부호벡터 주소를 부호화하는 방법이다. 실험을 통하여, 제안한 방법에서의 복원영상의 화질은 일반적인 벡터 양자화 방법에서의 복원영상의 화질과 동일하고 비트율은 약 45∼50% 감소함을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.31-34
• /
• 2000

In this paper, we proposed multispectral image compression method using CIP (classified inter-channel prediction) and SVQ (selective vector quantization) in wavelet domain. First, multispectral image is wavelet transformed and classified into one of three classes considering reflection characteristics of the subband with the lowest resolution. Then, for a reference channel which has the highest correlation with other channels, the variable VQ is performed in the classified intra-channel to remove spatial redundancy. For other channels, the CIP is performed to remove spectral redundancy. Finally, the prediction error is reduced by performing SVQ. Experiments are carried out on a multispectral image. The results show that the proposed method reduce the bit rate at higher reconstructed image quality and improve the compression efficiency compared to conventional method.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.979-982
• /
• 2002

Compressing image data by using Vector Quantization (VQ)［1］-［3］will compare Training Vectors with Codebook. The result is an index of position with minimum distortion. The implementing Random Codebook will reduce the image quality. This research presents the Splitting solution ［4］,［5］to implement the Codebook, which improves the image quality［6］by the average Training Vectors, then splits the average result to Codebook that has minimum distortion. The result from this presentation will give the better quality of the image than using Random Codebook.