• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.56-62
• /
• 2001

In this paper, we adopt a missing data theory to speech recognition. It can be used in order to maintain high performance of speech recognizer when the missing data occurs. In general, hidden Markov model (HMM) is used as a stochastic classifier for speech recognition task. Acoustic events are represented by continuous probability density function in continuous density HMM(CDHMM). The missing data theory has an advantage that can be easily applicable to this CDHMM. A marginalization method is used for processing missing data because it has small complexity and is easy to apply to automatic speech recognition (ASR). Also, a spectral subtraction is used for detecting missing data. If the difference between the energy of speech and that of background noise is below given threshold value, we determine that missing has occurred. We propose a new method that examines the reliability of detected missing data using voicing probability. The voicing probability is used to find voiced frames. It is used to process the missing data in voiced region that has more redundant information than consonants. The experimental results showed that our method improves performance than baseline system that uses spectral subtraction method only. In 452 words isolated word recognition experiment, the proposed method using the voicing probability reduced the average word error rate by 12％ in a typical noise situation.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.711-716
• /
• 2003

This paper proposes the method to select the number of optimal mixtures in each state in Continuous Density HMM (Hidden Markov Models), Previously, researchers used the same number of mixture components in each state of HMM regardless spectral characteristic of speaker, To model each speaker as accurately as possible, we propose to use a different number of mixture components for each state, Selection of mixture components considered the probability value of mixture by each state that affects much parameter estimation of continuous density HMM, Also, we use PCA (principal component analysis) to reduce the correlation and obtain the system' stability when it is reduced the number of mixture components, We experiment it when the proposed method used average 10% small mixture components than the conventional HMM, When experiment result is only applied selection of mixture components, the proposed method could get the similar performance, When we used principal component analysis, the feature vector of the 16 order could get the performance decrease of average 0,35% and the 25 order performance improvement of average 0.65%.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.5
• /
• pp.1172-1181
• /
• 1997

A militimedia data is a data mixed of formatted data like an audio and video. Multimedia data has characteristics that it need large amount of storage,wide network bandwith andreal time responsibolity. Because of these characteristocs, the VOD server and continous media storage server have a disk stripe structure or disk stripe sructure or disk array structure(RAID).In the parallel disk access system,high-speed play-back of continous media using segment interleavung may not ensure Qos pf other cioents because of the concentrated load within some disks. The load concentration of disks is related to both the number of disks in the system and playback rate of contimous media.In this paper. we describe that high-speed playback scheme,which is independent of the number of disk and plyback rate can be achieved by technique of changing the in-teval of access to segnent location.We show the experimental result of this technique in this pater.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.331.1-334
• /
• 1998

본 논문에서는 금액을 인식 대상으로 하는 음성 인식 시스템의 성능 향상을 위하여 프레임 동기 네트워크(Frame Synchronous Network)을 이용하였다. 연속음 인식에서 인식 대상이 가지는 규칙을 적용했을 경우 성능 향상을 가져올 수 있다. 금액이 가지는 반복적인 특성과 자릿수의 상하 관계가 인식 성능에 미치는 효과를 이용하여 다양한 수준의 제약을 갖는 FSN을 제안하였다. 제안된 FSN의 성능을 다양한 환경과 특징 벡터에 대하여 이산 hidden Markov model[5]을 이용하여 실험을 수행하였다. 인식 결과 제안된 FSN을 이용하여 금액 어휘의 인식 성능을 향상시킬 수 있었다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.470-474
• /
• 1998

In this paper, to estimate the time-varying parameters of speech signal, we use the robust sequential estimator based on t-distribution and, for time-varying signal, introduce the forgetting factor. By using the RSE based on t-distribution with small degree of freedom, we can alleviate efficiently the effects of outliers to obtain the better performance of parameter estimation. Moreover, by the forgetting factor, the proposed algorithm can estimate the accurate parameters under the rapid variation of speech signal.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.30-39
• /
• 2003

In this paper, we carried out the performance evaluation of HM-Net(Hidden Markov Network) speech recognition system for Korean speech databases. We adopted to construct acoustic models using the HM-Nets modified by HMMs(Hidden Markov Models), which are widely used as the statistical modeling methods. HM-Nets are carried out the state splitting for contextual and temporal domain by PDT-SSS(Phonetic Decision Tree-based Successive State Splitting) algorithm, which is modified the original SSS algorithm. Especially it adopted the phonetic decision tree to effectively express the context information not appear in training speech data on contextual domain state splitting. In case of temporal domain state splitting, to effectively represent information of each phoneme maintenance in the state splitting is carried out, and then the optimal model network of triphone types are constructed by in the parameter. Speech recognition was performed using the one-pass Viterbi beam search algorithm with phone-pair/word-pair grammar for phoneme/word recognition, respectively and using the multi-pass search algorithm with n-gram language models for sentence recognition. The tree-structured lexicon was used in order to decrease the number of nodes by sharing the same prefixes among words. In this paper, the performance evaluation of HM-Net speech recognition system is carried out for various recognition conditions. Through the experiments, we verified that it has very superior recognition performance compared with the previous introduced recognition system.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4
• /
• pp.24-31
• /
• 1996

In this paper, we present a speech translation system for hotel reservation, KT_STS(Korea Telecom Speech Translation System). KT-STS is a speech-to-speech translation system which translates a spoken utterance in Korean into one in Japanese. The system has been designed around the task of hotel reservation(dialogues between a Korean customer and a hotel reservation de나 in Japan). It consists of a Korean speech recognition system, a Korean-to-Japanese machine translation system and a korean speech synthesis system. The Korean speech recognition system is an HMM(Hidden Markov model)-based speaker-independent, continuous speech recognizer which can recognize about 300 word vocabularies. Bigram language model is used as a forward language model and dependency grammar is used for a backward language model. For machine translation, we use dependency grammar and direct transfer method. And Korean speech synthesizer uses the demiphones as a synthesis unit and the method of periodic waveform analysis and reallocation. KT-STS runs in nearly real time on the SPARC20 workstation with one TMS320C30 DSP board. We have achieved the word recognition rate of 94. 68% and the sentence recognition rate of 82.42% after the speech recognition tests. On Korean-to-Japanese translation tests, we achieved translation success rate of 100%. We had an international joint experiment in which our system was connected with another system developed by KDD in Japan using the leased line.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.5
• /
• pp.213-221
• /
• 2006

Phone segmentation of speech waveform is especially important for concatenative text to speech synthesis which uses segmented corpora for the construction of synthetic units. because the quality of synthesized speech depends critically on the accuracy of the segmentation. In the beginning. the phone segmentation was manually performed. but it brings the huge effort and the large time delay. HMM-based approaches adopted from automatic speech recognition are most widely used for automatic segmentation in speech synthesis, providing a consistent and accurate phone labeling scheme. Even the HMM-based approach has been successful, it may locate a phone boundary at a different position than expected. In this paper. we categorized adjacent phoneme pairs and analyzed the mismatches between hand-labeled transcriptions and HMM-based labels. Then we described the dominant error patterns that must be improved for the speech synthesis. For the experiment. hand labeled standard Korean speech DB from ETRI was used as a reference DB. Time difference larger than 20ms between hand-labeled phoneme boundary and auto-aligned boundary is treated as an automatic segmentation error. Our experimental results from female speaker revealed that plosive-vowel, affricate-vowel and vowel-liquid pairs showed high accuracies, 99%, 99.5% and 99% respectively. But stop-nasal, stop-liquid and nasal-liquid pairs showed very low accuracies, 45%, 50% and 55%. And these from male speaker revealed similar tendency.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.103-106
• /
• 1998

본 논문에서는 음성인식 시스템의 인식 정도의 향상을 위해서 동적 특징으로서 K-L(Karhanen-Loeve)계수를 이용하여 음소모델을 구성하는 방법을 제안하고, 음소, 단어, 숫자음 인식 실험을 통하여 그 유효성을 검토하였다. 인식 실험을 위한 음성자료는 한국 전자통신 연구소에서 채록한 445단어와 국어정보공학연구소에서 채록한 4연속 숫자음을 사용하였으며, K-L계수 동적 특징의 유효성을 확인하기 위해 정적 특징으로서 멜-켑스트럼과 동적 특징으로서 K-L계수 및 회귀계수를 추출한 후 음소, 단어, 숫자음 인식 실험을 수행하였다. 인식의 기본 단위로는 48개의 유사음소단위(Phoneme Likely Unite ; PLUs)를 음소모델로 사용하였으며, 단어와 숫자음 인식을 위해서는 유한상태 오토마타(Finite State Automata; FSA)에 의한 구문제어를 통한 OPDP(One Pass Dynamic Programming)법을 이용하였다. 인식 실험 결과, 음소인식에 있어서는 정적특징인 멜-켑스트럼을 사용한 경우 39.8%, K-L 동적 계수를 사용한 경우가 52.4%로 12.6%의 향상된 인식률을 얻었다. 또한, 멜-켑스트럼과 회수계수를 사용한 경우 60.1%, K-L계수와 회귀계수를 결합한 경우에 있어서도 60.4%로 높은 인식률은 얻었다. 이 결과를 단어인식에 확장하여 인식 실험을 수행한 결과, 기존의 멜-켑스트럼 계수를 사용한 경우 65.5%, K-L계수를 사용한 경우 75.8%로 10.3% 향상된 인식률을 얻었으며, 멜-켑스트럼과 회귀계수를 결합한 경우 91.2%, K-L계수와 회귀계수를 결합한 경우 91.4%의 높은 인식률을 보였다. 도한, 4연속 숫자음에 적용한 경우에 있어서도 멜-켑스트럼을 사용한 경우 67.5%, K-L계수를 사용한 경우 75.3%로 7.8%의 향상된 인식률을 보였으며 K-L계수와 회귀계수를 결합한 경우에서도 비교적 높은 인식률을 보여 숫자음에 대해서도 K-L계수의 유효성을 확인할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.62-70
• /
• 2000

In usual language models(LMs), the probability has been estimated by selecting highly frequent words from a large text side database. However, in case of adopting LMs in a specific task, it is unnecessary to using the general method; constructing it from a large size tent, considering the various kinds of cost. In this paper, we propose a construction method of LMs using a small size text database in order to be used in specific tasks. The proposed method is efficient in increasing the low frequent words by applying same sentences iteratively, for it will robust the occurrence probability of words as well. We carried out continuous speech recognition(CSR) experiments on 200 sentences uttered by 3 speakers using LMs by iterative teaming(IL) in a air flight reservation task. The results indicated that the performance of CSR, using an IL applied LMs, shows an 20.4% increased recognition accuracy compared to those without it. This system, using the IL method, also shows an average of 13.4% higher recognition accuracy than the previous one, which uses context-free grammar(CFG), implying the effectiveness of it.