• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.2
• /
• pp.276-283
• /
• 1994

Using a neural network for vector quantization, we can expect to have better codebook design algorithm for its adaptive process. Also, the designed codebook puts the codewords in order by its self-organizing characteristics, which makes it possible to partially search the codebook for real time process. To exploit these features of the neural network, in this paper, we propose a new codebook design algorithm that modified the KSFM(Kohonen`s Self-organizing Feature Map) and then combines the K-means algorithm. Experimental results show the performance improvment and the ability of the partical seach of the codebook for the real time process.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.143-146
• /
• 2001

본 논문에서는 랜덤초기화 방법을 사용하여 초기 코드북을 생성하고, 이를 이용하여 초기 반복학습 시 수렴영역을 벗어난 2 이상의 가중치에 의한 K-means 알고리즘을 제안한다. 기존의 K-means 알고리즘이 국부적으로 최적화되고 초기 반복학습 시에 가중치의 영향이 크다는 점을 이용하여, 제안된 방법에서는 초기 반복학습 시의 가중치를 수렴영역에서 벗어난 큰 값으로 주고 이후 반복학습시의 가증치는 수렴영역 안에 있는 값으로 고정하여 코드북을 설계한다. 또한 초기 코드북을 얻기 위해 Splitting 방법과 같은 추가적인 과정 없이 랜덤한 방법에 의한 초기 코드북을 적용함으로써 제안된 알고리즘이 단순한 구조를 가지며, 구해진 코드북의 성능도 우수함을 확인할 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.374-376
• /
• 2000

음성인식 시스템에 사용하는 알고리즘 중에 하나인 DHMM은 코드북을 이용하여 음성의 프레임들에 대한 특징을 관측열로 추출하여 음성의 패턴에 대한 훈련과 인식을 수행하게 된다. 그러나 음성은 유성음과 무성음의 특징 차이가 많이 나게 되므로 하나의 코드북을 이용하게 되면 코드북 오차에 의하여 성질이 전혀 다른 코드북 인덱스를 DHMM의 관측열로 사용하게 된다. 본 논문에서는 음성의 유성음과 무성음에 대한 선별적인 작업을 통해 서로 다른 코드북을 만들어 관측열을 추출하고 선행 관측과 현 관측과의 거리 비교 연산을 통하여 관측의 시간축을 정규화한 관측열을 음성인식에 사용하였다. 본 논문에서 제시하는 인식 방법을 사용하여 실험한 결과, 기존의 인식 방법보다 5.33% 향상된 결과를 얻었다.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.167-172
• /
• 2002

The EVRC (Enhanced Variable Rate Codec) is currently in service as a speech cosec in digital cellular systems in North America and Korea. In the EVRC, the LSP (Line Spectral Pairs) related to energy distribution of speech signals in the frequency domain are coded by weighted split vector quantization. Considering that the LSP codebooks might be trained with the language of the develop country of the codebooks or English, it is expected that codebooks trained with Korean provide the performance improvements in the communication in Korean. In this paper, the EVRC LSP codebooks are designed with korean adopting the LBG algorithm based vector quantization, and the performance improvement of the vector quantization and the accompanying speech quality improvement are demonstrated by spectral distortion, SNR and SegSNR measurements, respectively.

• Journal of Digital Contents Society
• /
• v.13 no.3
• /
• pp.309-315
• /
• 2012

Active data are the input data which are changed its membership as Vector Quantization codebook generation algorithm is processed. In the process of VQ codebook generation algorithm performed, the actual active data out of the entire input data will be less presented as the process is performed. Therefore, if we can accurately find the active data and only if we are going to do VQ codebook generation on the active data, then we can significantly reduce the overall generation time. In this paper, we presented the triangle inequality based algorithm to select the active data. Experimental results show that our algorithm is superior to other methods in terms of the VQ codebook generation time.

• Journal of Digital Contents Society
• /
• v.17 no.5
• /
• pp.375-381
• /
• 2016

Recently, a foreground-background segmentation using codebook model has been researched actively. The codebook is created one for each pixel in the image. The codewords are vector-quantized representative values of same positional training samples from the input image sequences. The training is necessary for a long time in the most of codebook-based algorithms. In this paper, the initial codebook model is generated simply using median operation with several image frames. The initial codebook is updated to adapt the dynamic changes of backgrounds based on the frequencies of codewords that matched to input pixel during the detection process. We implemented the proposed algorithm in the environment of visual c++ with opencv 3.0, and tested to some of the public video sequences from PETS2009. The test sequences contain the various scenarios including quasi-periodic motion images, loitering objects in the local area for a short time, etc. The experimental results show that the proposed algorithm has good performance compared to the GMM algorithm and standard codebook algorithm.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.21-28
• /
• 2016

We propose an adaptive scheme of a differential codebook for temporally correlated channels. And the codeword entries of the propose codebook are selected among the set of M-PSK constellations - the values of M proposed in this paper are 8, 16, or 32. Firstly, we analyze mathematically how the optimal spherical cap radius of the proposed codebook is tracked. Then, we explain the practical implementation of the proposed adaptive method. Practically, some candidate differential codebooks we propose in this paper can be switched according to the temporal correlation coefficients of wireless channels in the proposed scheme. Monte-Carlo simulations demonstrate that the achievable throughput performance employing the proposed codebook is always superior to those of the differential codebooks employing M-PSK constellations and non-adaptive differential codebooks with the same amount of feedback information.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1991.06a
• /
• pp.50-53
• /
• 1991

벡터 양지화(VQ)는 신호 처리분야에서 정보의 압축을 위해 사용하는 아주 잘 알려진 방법이다. 벡터 양지화는 정보를 대량으로 줄이면서 그 효율을 떨어 뜨리지 않는 방향으로 발전해 왔다. VQ코드북의 크기가 커지면 하나의 코드워드를 찾기위한 시간이 증가하게 된다. 코드북의 빠른 검색을 위하여 다른 방법에 제안 되기도 했으나 최적 검색 방법이라고는 볼 수 없다. 본 고에서는 음성인식에 적용할 목적으로 기존의 방법으로 구성된 코드북의 구성을 변형 하지 않고 검색 속도를 증가 시킬 수 있는 방법을 기수랗고 그 효율에 대해서 설명한다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.10
• /
• pp.3272-3279
• /
• 2000

In this paper, we propose two fast VQ coclebook search algorithms efficient to the Wavelet/ VQ coding schemes. It is well known that the probability having large values in wavelet coefficient blocks is very low. In order to apply this property to codebook search, the index tables of the reordered codebook in each wavelet subband ae used. The exil condition in PDE can be satisfied in an earlystage by comparing the large coefficients of the codeword with their corresponding elements of input vector using the index tbles. As a result, search time can be reduced.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.165-170
• /
• 2014

Speech enhancement techniques that remove surrounding noise are stressed to preprocessor of speech recognition. Among the various speech enhancement techniques, Codebook-based Speech Enhancement (CBSE) operates efficiently in non-stationary noise environments. But, CBSE has some problems that inaccurate gains can be estimated if mismatch occur between input noisy signal and trained speech/noise codevectors. In this paper, the Normalized Weighting Factor (NWF) is calculated by long-term noise estimation algorithm based on Signal-to-Noise Ratio, compensated to the conventional inaccurate gains. The proposed CBSE shows better performance than conventional CBSE.