• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.167-179
• /
• 2002

In this paper, we propose a new acoustic model for characterizing segmental features and an algorithm based upon a general framework of hidden Markov models (HMMs) in order to compensate the weakness of HMM assumptions. The segmental features are represented as a trajectory of observed vector sequences by a polynomial regression function because the single frame feature cannot represent the temporal dynamics of speech signals effectively. To apply the segmental features to pattern classification, we adopted segmental HMM(SHMM) which is known as the effective method to represent the trend of speech signals. SHMM separates observation probability of the given state into extra- and intra-segmental variations that show the long-term and short-term variabilities, respectively. To consider the segmental characteristics in acoustic model, we present segmental-feature HMM(SFHMM) by modifying the SHMM. The SFHMM therefore represents the external- and internal-variation as the observation probability of the trajectory in a given state and trajectory estimation error for the given segment, respectively. We conducted several experiments on the TIMIT database to establish the effectiveness of the proposed method and the characteristics of the segmental features. From the experimental results, we conclude that the proposed method is valuable, if its number of parameters is greater than that of conventional HMM, in the flexible and informative feature representation and the performance improvement.

• MALSORI
• /
• no.43
• /
• pp.163-178
• /
• 2002

In this paper, we discuss the characteristics of Segmental-Feature HMM and summarize previous studies of SFHMM. There are several approaches to reduce the number of parameters in the previous studies. However, if the number of parameters decreased, the performance of systems also fell. Therefore, we consider the fast computation approach with preserving the same number of parameters. In this paper, we present the new segment comparison method to speed up the computation of SFHMM without loss of performance. The proposed method uses the three-frame calculation rather than the full(five) frames in the given segment. The experimental results show that the performance of the proposed system is better than that of the previous studies.

• MALSORI
• /
• no.62
• /
• pp.113-131
• /
• 2007

It is reported that the segmental feature based recognition system shows better results than conventional feature based system in the previous studies. On the other hand, the various studies of combining neural network and hidden Markov models within a single system are done with expectations that it may potentially combine the advantages of both systems. With the influence of these studies, tandem approach was presented to use neural network as the classifier and hidden Markov models as the decoder. In this paper, we applied the trend information of segmental features to tandem architecture and used posterior probabilities, which are the output of neural network, as inputs of recognition system. The experiments are performed on Auroral database to examine the potentiality of the trend feature based tandem architecture. From the results, the proposed system outperforms on very low SNR environments. Consequently, we argue that the trend information on tandem architecture can be additionally used for traditional MFCC features.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.7
• /
• pp.641-647
• /
• 2002

In this paper, we propose the reduction method of the number of parameters in the segmental-feature HMM using trend quantization method. The proposed method shares the trend information of the polynomial trajectories by quantization. The trajectory is obtained by the sequence of feature vectors of speech signals and can be divided by trend and location information. The trend indicates the variation of consequent frame features, while the location points to the positional difference of the trajectories. Since the trend occupies the large portion of SFHMM, if the trend is shared, the number of parameters maybe decreases. To exploit the proposed system the experiments are performed on TIMIT corpus. The experimental results show that the performance of the proposed system is roughly similar to that of previous system. Therefore, the proposed system can be considered one of parameter reduction method.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.7
• /
• pp.48-52
• /
• 2000

음성 인식에 많이 사용되는 HMM (hidden Markov model)을 개선하기 위하여 분절 특징을 사용한 분절 특징 HMM은 성능이 우수하다고 발표되었다. 그러나, 분절 길이가 증가하고 회귀 차수가 놓아질수록 분절 특징 HMM을 표현하는 매개 변수의 수도 같이 증가된다. 따라서, 본 연구에서는 상태에서 관측 가능한 분절의 분산을 분절 내의 모든 프레임에 대하여 공통적으로 표현하는 고정 분산 방법을 통하여 성능의 저하 없이 매개 변수의 수를 줄이도록 시도하였다. 실험 결과, 두 혼합 밀도인 경우 고정 분산을 이용한 분절 특징 HMM의 성능과 시변 분산을 이용한 성능의 차이가 거의 없어, 제안된 방법의 유효성을 입증하였다.

• MALSORI
• /
• no.57
• /
• pp.113-122
• /
• 2006

Recently, many studies have been done for speech recognition in noisy environments. Particularly, the Aurora DB has been built as the common database for comparing the various feature extraction schemes. However, in general, the recognition models as well as the features have to be modified for effective noisy speech recognition. As the structure of the HTK is very complex, it is not easy to modify, the recognition engine. In this paper, we implemented a baseline recognizer based on the segmental K-means algorithm whose performance is comparable to the HTK in spite of the simplicity in its implementation.

• Journal of Environmental Health Sciences
• /
• v.24 no.3
• /
• pp.35-40
• /
• 1998

This study was conducted to examine the pathological changes of rat peripheral nervous system during exposure to tellurium known to be a demyelinating agent by using teasing nerve fiber method and quantitative light microscopic analysis by image analyzer. The pellet containing 1.2% of tellurium were fed for 3, 5, 7, 9, 13 days to male wistar rats (21 days old) and then neurologic symptom and the feature of nerve fiber myelination were studied. From this study, following results were obtained. In 3 days treated group, it showed various neurologic symptom and teased nerve fiber showed slight irregularity of the myeline sheath. In 5 days and 7 days treated groups, it showed the segmental demyetination in larger size fiber and widening of nodes of ranvier. In 9 days and 13 days treated groups, the remyelinated fibers were observed and it was generally small in size. We consequently suggest that teasing nerve fiber method and quantitative analysis of nerve fiber were useful pathologic screening method of neurotoxicity of the peripheral nervous system.

• Childhood Kidney Diseases
• /
• v.9 no.2
• /
• pp.237-244
• /
• 2005

Membranoproliferative glomerulonephritis (MPGN) is a progressive primary glomerulonephritis characterized by mesangial proliferation with increased mesangial matrix, subendothelial immune deposits, mesangial interposition and a double contour feature of the glomerular basement membrane. The glomerular involvement in MPGN is usually diffuse, however, cases of focal or segmental MPGN have been reported by several authors. We report a case of focal segmental MPGN with prolonged hypocomplementemia for ,3 years in a 5 years old girl. (J Korean Soc Pediatr Nephrol 2005;9:237-244)

• Childhood Kidney Diseases
• /
• v.17 no.1
• /
• pp.13-18
• /
• 2013

Podocytopathy is glomerular lesions characterized by podocyte injury. It is observed in various glomerular diseases, but minimal change disease and focal segmental glomerulosclerosis (FSGS) are the prototypes. In this review, morphologic features of podocyte injury and subtypes of FSGS will be reviewed briefly. Effacement of podocyte foot processes is the most common feature of podocyte injury. As podocytic injury progresses, intracytoplasmic vacuoles, subpodocytic cyst, detachment of podocytes from the glomerular basement membrane and apoptosis develop. Glomerular capillary loops in epithelium-denuded area undergo capillary collapse. Synechia and hyalinosis may accompany this lesion. To manifest segmental sclerosis, podocyte loss above a threshold level may be required. Injured podocytes can injure neighboring intact podocytes, and thereby spread injury within the same lobule. FSGS can be categorized into five subtypes by morphologic characteristics; not otherwise specified (NOS), perihilar, cellular, tip, and collapsing types. Each subtype has been reported to show different clinical courses and associated conditions, but there are controversies on its significance. With recent progress in the discovery of genetic abnormalities causing FSGS and plasma permeability factors, we expect to unravel pathophysiology of FSGS and to understand histological sequences leading to FSGS in near future.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.35-44
• /
• 2000

In this paper, we propose a new trajectory model for characterizing segmental features and their interaction based upon a general framework of hidden Markov models. Each segment, a sequence of vectors, is represented by a trajectory of observed sequences. This trajectory is obtained by applying a new design matrix which includes transitional information on contiguous frames, and is characterized as a polynomial regression function. To apply the trajectory to the segmental HMM, the frame features are replaced with the trajectory of a given segment. We also propose the likelihood of a given segment and the estimation of trajectory parameters. The obervation probability of a given segment is represented as the relation between the segment likelihood and the estimation error of the trajectories. The estimation error of a trajectory is considered as the weight of the likelihood of a given segment in a state. This weight represents the probability of how well the corresponding trajectory characterize the segment. The proposed model can be regarded as a generalization of a conventional HMM and a parametric trajectory model. The experimental results are reported on the TIMIT corpus and performance is show to improve significantly over that of the conventional HMM.