• Speech Sciences
• /
• v.15 no.2
• /
• pp.67-77
• /
• 2008

In this paper, we implemented a robust speech recognizer using the TMS320VC33 DSP. For this implementation, we had built speech and noise database suitable for the recognizer using spectral subtraction method for noise removal. The recognizer has an explicit structure in aspect that a speech signal is enhanced through spectral subtraction before endpoints detection and feature extraction. This helps make the operation of the recognizer clear and build HMM models which give minimum model-mismatch. Since the recognizer was developed for the purpose of controlling car facilities and voice dialing, it has two recognition engines, speaker independent one for controlling car facilities and speaker dependent one for voice dialing. We adopted a conventional DTW algorithm for the latter and a continuous HMM for the former. Though various off-line recognition test, we made a selection of optimal conditions of several recognition parameters for a resource-limited embedded recognizer, which led to HMM models of the three mixtures per state. The car noise added speech database is enhanced using spectral subtraction before HMM parameter estimation for reducing model-mismatch caused by nonlinear distortion from spectral subtraction. The hardware module developed includes a microcontroller for host interface which processes the protocol between the DSP and a host.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.624-629
• /
• 2018

Classification of moving targets in Pulse Doppler Radar(PDR) for surveillance and reconnaissance purposes is generally carried out based on listening and training experience of Doppler audio signals by radar operator. In this paper, we proposed the automatic classification method to identify the class of moving target with Doppler audio signals using the Mel Frequency Cepstral Coefficients(MFCC) and the Hidden Markov Model(HMM) algorithm which are widely used in speech recognition and the classification performance was analyzed and verified by simulations.

• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1540-1549
• /
• 2004

In this paper, we propose an algorithm to detect semantic events in golf video using Hidden Markov Model. The purpose of this paper is to identify and classify the golf events to facilitate highlight-based video indexing and summarization. In this paper we first define 4 semantic events, and then design HMM model with states made up of each event. We also use 10 multiple visual features based on MPEG-7 visual descriptors to acquire parameters of HMM for each event. Experimental results showed that the proposed algorithm provided reasonable detection performance for identifying a variety of golf events.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.6
• /
• pp.46-50
• /
• 2001

This paper proposes a new recognition time reduction algorithm Score-Cache technique, which is applicable to the HMM-base speech recognition system. Score-Cache is a very unique technique that has no other performance degradation and still reduces a lot of search time. Other search reduction techniques have trade-offs with the recognition rate. This technique can be applied to the continuous speech recognition system as well as the isolated word speech recognition system. W9 can get high degree of recognition time reduction by only replacing the score calculating function, not changing my architecture of the system. This technique also can be used with other recognition time reduction algorithms which give more time reduction. We could get 54% of time reduction at best.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.384-386
• /
• 1998

The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction(HCI). Many methods hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network(NN), Hidden Markov Model(HMM) and so on. In our research, a HMMs is proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin-color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and thus, produces a trajectory. The spotting a feature database, the proposed approach use the mesh feature code for codebook of HMM. In our experiments, 1300 alphabetical and 1300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfying recognition rate for the images with different sizes, shapes and skew angles.

• Journal of KIISE:Information Networking
• /
• v.29 no.6
• /
• pp.674-684
• /
• 2002

Anomaly detection techniques have teen devised to address the limitations of misuse detection approach for intrusion detection. An HMM is a useful tool to model sequence information whose generation mechanism is not observable and is an optimal modeling technique to minimize false-positive error and to maximize detection rate, However, HMM has the short-coming of login training time. This paper proposes an effective HMM-based IDS that improves the modeling time and performance by only considering the events of privilege flows based on the domain knowledge of attacks. Experimental results show that training with the proposed method is significantly faster than the conventional method trained with all data, as well as no loss of recognition performance.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1991.06a
• /
• pp.54-57
• /
• 1991

본 논무에서는 HMM과 VQ를 이용한 고립단어에 대한 화자종속 및 화자독립 음성인식시스템을 만들고 여기에 화자적응을 하는 방법에 대한 연구를 했다. 화자적응방법에는 크게 VQ코드북을 적응시키는 방법과 HMM패러미터블 적응시키는 방법이 있다. 코드북적응을 하는 방법으로서 기존코드북에 대해 새로운화자의 적응음성을 양자화한 뒤 각 코드벡터에 해당하는 적응음성의 평균을 구해서 새로운 화자의 코드북을 구해주는 방법과 기준코드북에 대해 새로운화자의 적응음성을 양자화할 때 HMM의 각 상태에서 각각의 코드벡터를 발생할 확률을 거리오차의 계산에서 고려해 비록 거리오차는 크지만 그 코드벡터를 발생할 확률이 매우 높으면 적응음성이 그 코드벡터에 index되게해서 각 코드벡터에 해당하는 모든 적응음성데이타의 평균을 새로운 코드북으로 하는 두가지 알고리즘을 제안한다. 이렇게 함으로써 기존의 기준코드북을 초기 코드북으로해서 LBG알고리즘을 사용해서 적응음성데이타에 대한 새로운 코드북을 만드는 방법에 비해 5-10배의 계산시간을 감소하게 된다. 이 새로운 코드북으로 적응음성데이타를 다시 index해서 이 index된 음성렬로 HMM패러미터를 적응했다. 제안된 알고리즘이 코드북적응을 하는 경우에 기존의 적응방법에 비해 5-10배의 계산 시간을 단축하면서 인식률에서는 더 나은결과를 얻었다. 또 같은 적응방법에 대해서 화자종속모델 보다는 화자독립모델에 대해서 화자적응하는 것이 더 나은 인식결과를 보여주었다.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.2E
• /
• pp.25-32
• /
• 1995

In this paper, we propose to use a parallel-branch subunit model for improved word recognition. The model is obtained by splitting off each subunit branch based on mixture component in continuous hidden Markov model(continuous HMM). According to simulation results, the proposed model yields higher recognition rate than the single-branch subunit model or the parallel-branch subunit model proposed by Rabiner et al[1]. We show that a proper combination of the number of mixture components and the number of branches for each subunit results in increased recognition rate. To study the recognition performance of the proposed algorithms, the speech material used in this work was a vocabulary with 1036 Korean words.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.200-207
• /
• 2001

In this paper, we propose an HMM(Hidden Markov modeJ)-MLP(Multi-layer perceptron) hybrid model for recognizing legal words on the English bank check. We adopt an explicit segmentation-based word level architecture to implement an HMM engine with nonscaled and non-normalized symbol vectors. We also introduce an MLP for implicit segmentation-based word recognition. The final recognition model consists of a hybrid combination of the HMM and MLP with a new hybrid probability measure. The main contributions of this model are a novel design of the segmentation-based variable length HMMs and an efficient method of combining two heterogeneous recognition engines. ExperimenLs have been conducted using the legal word database of CENPARMI with encouraging results.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.391-394
• /
• 2004

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 24.5kbytes for program code. Maximum required time of 29.2ms for processing a frame of 32ms of speech validates real-time operation of the implemented system.