• 말소리와 음성과학
• /
• 제6권1호
• /
• pp.77-83
• /
• 2014

This paper proposes a speaker and environment clustering method in order to overcome the degradation of the speech recognition performance caused by various noise and speaker characteristics. In this paper, instead of using the distance between Gaussian mixture model (GMM) weight vectors as in the Google's approach, the distance between the adapted mean vectors based on the modified maximum a posteriori (MAP) adaptation is used as a distance measure for vector quantization (VQ) clustering. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method yields error rate reduction of 10.6% compared with baseline speaker-independent (SI) model, which is slightly better performance than the Google's approach.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2004년도 추계학술발표대회논문집 제23권 2호
• /
• pp.299-302
• /
• 2004

본 논문에서는 내용 기반 음악 정보 검색에 음악의 temporal 특징을 이용한 검색 방법을 제안한다. 방송환경에 적용하기 위해 검색 범위를 드라마나 영화의 배경 음악으로 사용되는 OST 앨범으로 제한하였다. 오디오의 특징 벡터로써 UFCC(Mel Frequency Cepstral Coefficient)를 사용하였으며 이 특징 벡터를 이용하여 VQ(Vector Quantization)로 부호화한 codeword로 오디오 신호의 시변 특성을 표현한다. 본 논문에서는 제안한 음악의 temporal 특성을 반영한 codeword-sequence를 이용하는 방법을 pitch-histogram을 기반으로 하는 방법 및 MFCC codeword-histogram을 기반으로 하는 방법과 비교하고 성능 개선을 보여주었다.

• 대한음성학회지:말소리
• /
• 제57호
• /
• pp.99-112
• /
• 2006

In this paper, we introduce two retrieval methods for photos with speech documents. We compare the pattern of speech query with those of speech documents recorded in digital cameras, and measure the similarities, and retrieve photos corresponding to the speech documents which have high similarity scores. As the first approach, a phoneme recognition scheme is used as the pre-processor for the pattern matching, and in the second one, the vector quantization (VQ) and the dynamic time warping (DTW) are applied to match the speech query with the documents in signal domain itself. Experimental results show that the performance of the first approach is highly dependent on that of phoneme recognition while the processing time is short. The second method provides a great improvement of performance. While the processing time is longer than that of the first method due to DTW, but we can reduce it by taking approximated methods.

• 한국지능시스템학회논문지
• /
• 제14권2호
• /
• pp.201-206
• /
• 2004

This study attempted to develop a speech recognition module applied to a wheelchair for the physically handicapped. In the proposed speech recognition module, TMS320C32 was used as a main processor and Mel-Cepstrum 12 Order was applied to the pro-processor step to increase the recognition rate in a noisy environment. DTW (Dynamic Time Warping) was used and proven to be excellent output for the speaker-dependent recognition part. In order to utilize this algorithm more effectively, the reference data was compressed to 1/12 using vector quantization so as to decrease memory. In this paper, the necessary diverse technology (End-point detection, DMA processing, etc.) was managed so as to utilize the speech recognition system in real time

• 음성과학
• /
• 제2권
• /
• pp.57-66
• /
• 1997

This paper studies the effects of the method, CMS(Cepstral Mean Subtraction), (which compensates for some of the speech distortion. caused by telephone channels), on the performance of the text-dependent speaker identification system. This system is based on the VQ(Vector Quantization) and HMM(Hidden Markov Model) method and chooses the LPC-Cepstrum and Mel-Cepstrum as the feature vectors extracted from the speech data transmitted through telephone channels. Accordingly, we can compare the correct recognition rates of the speaker identification system between the use of LPC-Cepstrum and Mel-Cepstrum. Finally, from the experiment results table, it is found that the Mel-Cepstrum parameter is proven to be superior to the LPC-Cepstrum and that recognition performance improves by about 10% when compensating for telephone channel using the CMS.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2002년도 춘계학술발표논문집 (상)
• /
• pp.97-100
• /
• 2002

이미지, 비디오, 오디오와 같은 멀티미디어 데이터들은 텍스트기반의 데이터에 비하여 대용량이고 비정형적인 특성을 가지기 때문에 검색이 어렵다. 또한 멀티미디어 데이터의 특징은 행렬이나 벡터의 형태로 표현되기 때문에 완전일치 검색이 아닌 유사 검색을 수행하여 사용자가 원하는 이미지와 유사한 이미지를 검색해야 한다. 본 연구에서는 멀티미디어 데이터 검색에 클러스터링와 인덱싱 기법을 같이 적용하여 유사한 이미지끼리는 인접 디스크에 클러스터하고 이 클러스터에 접근하는 인덱스를 구축하여 검색이 빠르게 이루어지는 유사 검색방법을 제안한다 제안 검색 방법은 클러스터링을 생성하는 알고리즘과 해싱기법의 인덱싱을 같이 적용함으로써 VQ(Vector Quantization)보다 높은 재현율과 정확도를 보인다.

• 대한의용생체공학회:의공학회지
• /
• 제14권2호
• /
• pp.177-183
• /
• 1993

Medical imagies with high resolution are coded to be archived and communicated in MPACS. In this paper, we have studied on coding of Cardio-Angiography. Our coding technique is Subband-Vector Quantization. This techniques is irreversible coding method. This technique's advantages are removing blocking artifact and edge degradation, adapting for drastic image change because of dye injection, and fast decoding. We achieved good results for Cardio-Angiography data, but the study on more sophiscated motion estimation techniques and VQ techniques must be performed.

• 한국유체기계학회 논문집
• /
• 제7권2호
• /
• pp.41-49
• /
• 2004

Condition monitoring is very important in turbo machinery because single failure could cause critical damages to its plant. So, automatic fault recognition has been one of the main research topics in condition monitoring area. We have used a relatively new fault recognition method, Hidden Markov Model(HMM), for mechanical system. It has been widely used in speech recognition, however, its application to fault recognition of mechanical signal has been very limited despite its good potential. In this paper, discrete HMM(DHMM) was used to recognize the faults of rotor system to study its fault recognition ability. We set up a rotor kit under unbalance and oil whirl conditions and sampled vibration signals of two failure conditions. DHMMS of each failure condition were trained using sampled signals. Next, we changed the setup and the rotating speed of the rotor kit. We sampled vibration signals and each DHMM was applied to these sampled data. It was found that DHMMs trained by data of one rotating speed have shown good fault recognition ability in spite of lack of training data, but DHMMs trained by data of four different rotating speeds have shown better robustness.

• 대한전자공학회논문지SP
• /
• 제49권1호
• /
• pp.11-18
• /
• 2012

본 논문에서는 고 전송률에서도 구현이 가능한 엔트로피 제한(entropy constrained) 벡터양자기를 제안하였다. 양자화는 프로덕트 부호책에 기초한 프로덕트 표본 적응 양자기(sample-adaptive product quantizer)를 사용하여 엔트로피 제한 SAPQ(ECSAPQ) 설계 알고리듬을 제안하고 실험을 통하여 성능을 비교해 보았다. 제안한 ECSAPQ는 비슷한 복잡도의 엔트로피 제한 VQ보다 약 0.5dB 정도 성능이 좋음을 알 수 있었다. 또한 스칼라 양자기에 기초한 ECSAPQ는 Shannon의 최저 왜곡 곡선과 1.53dB의 차이를 가지는 ECSQ의 고 전송률에서의 이론 곡선보다 더 낮은 왜곡 곡선을 가짐을 확인할 수 있었다.

• 전자공학회논문지CI
• /
• 제37권5호
• /
• pp.54-63
• /
• 2000

본 논문에서는 음성인식, 음성합성, Motion Tracking, 3D Animation이 가능한 가상캐릭터를 구현하였다. 음성인식으로는 K-means 128 Level VQ와 MFCC의 특징패턴을 바탕으로 Discrete-HMM 알고리즘을 이용하였다. 음성합성에는 반음절 단위의 TD-PSOLA를 이용하였으며, Motion Tracking에서는 계산량을 줄이기 위해 Fast Optical Flow Like Method를 제안하고, 3D Animation 시스템은 Vertex Interpolation방법으로 Animation을 하고 Direct3D를 이용하여 Rendering을 하였다. 최종적으로 위에 나열된 시스템들을 통합하여 사용자를 계속적으로 주시하면서 사용자와 함께 구구단 게임을 할 수 있는 가상캐릭터를 구현하였다.