• Journal of Korea Multimedia Society
• /
• v.4 no.6
• /
• pp.524-533
• /
• 2001

Efficient continuous speech recognition system for practical applications requires that the processing be carried out in real time and high recognition accuracy. In this paper, we study the acoustic models by adopting the PDT-SSS algorithm and the language models by iterative learning so as to improve the speech recognition accuracy. And the adaptive pruning algorithm is applied to the continuous speech. To verify the effectiveness of proposed method, we carried out the continuous speech recognition for the Korean air flight reservation task. Experimental results show that the adopted algorithm has the average 90.9% for continuous speech recognition and the average 90.7% for word recognition accuracy including continuous speech. And in case of adopting the adaptive pruning algorithm to continuous speech, it reduces the recognition time of about 1.2 seconds(15%) without any loss of accuracy. From the result, we proved the effectiveness of the PDT-SSS algorithm and the adaptive pruning algorithm.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.9-15
• /
• 2001

In this paper we investigate context dependent acoustic models to improve the performance of the Korean speech recognition . The algorithm are using the Korean phonological rules and decision tree, By Successive State Splitting(SSS) algorithm the Hidden Merkov Netwwork(HM-Net) which is an efficient representation of phoneme-context-dependent HMMs, can be generated automatically SSS is powerful technique to design topologies of tied-state HMMs but it doesn't treat unknown contexts in the training phoneme contexts environment adequately In addition it has some problem in the procedure of the contextual domain. In this paper we adopt a new state-clustering algorithm of SSS, called Phonetic Decision Tree-based SSS (PDT-SSS) which includes contexts splits based on the Korean phonological rules. This method combines advantages of both the decision tree clustering and SSS, and can generated highly accurate HM-Net that can express any contexts To verify the effectiveness of the adopted methods. the experiments are carried out using KLE 452 word database and YNU 200 sentence database. Through the Korean phoneme word and sentence recognition experiments. we proved that the new state-clustering algorithm produce better phoneme, word and continuous speech recognition accuracy than the conventional HMMs.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.727-739
• /
• 2003

In this paper, we propose a generation method of regression classes for adaptation in the HM-Net (Hidden Markov Network) system. The MLLR (Maximum Likelihood Linear Regression) adaptation approach is applied to the HM-Net speech recognition system for expressing the characteristics of speaker effectively and the use of HM-Net in various tasks. For the state level sharing, the context domain state splitting of PDT-SSS (Phonetic Decision Tree-based Successive State Splitting) algorithm, which has the contextual and time domain clustering, is adopted. In each state of contextual domain, the desired phoneme classes are determined by splitting the context information (classes) including target speaker's speech data. The number of adaptation parameters, such as means and variances, is autonomously controlled by contextual domain state splitting of PDT-SSS, depending on the context information and the amount of adaptation utterances from a new speaker. The experiments are performed to verify the effectiveness of the proposed method on the KLE (The center for Korean Language Engineering) 452 data and YNU (Yeungnam Dniv) 200 data. The experimental results show that the accuracies of phone, word, and sentence recognition system increased by 34∼37%, 9%, and 20%, respectively, Compared with performance according to the length of adaptation utterances, the performance are also significantly improved even in short adaptation utterances. Therefore, we can argue that the proposed regression class method is well applied to HM-Net speech recognition system employing MLLR speaker adaptation.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.366-369
• /
• 2003

본 연구에서는 강건한 문맥의존 음향모델을 작성하기 위한 기초적인 연구로서 문맥환경과 상태수의 변화에 따른 음향모델의 성능을 고찰하고자 한다. 음성은 시간함수로 표현되며 음절, 단어, 연속음성을 발성할때 자음과 모음에 따라 발성시간에 차이가 있으며 음성인식의 최소 인식단위로 널리 사용되는 음소의 앞과 뒤에 오는 문맥환경에 따라 인식성능에 많은 차이를 보이고 있다. 따라서 본 연구에서는 시간의 변화(상태수의 변화)와 상태분할 과정에서 문맥환경의 변화를 고려하여 다양한 형태의 문맥의존 음향모델을 작성하였다. 모델학습은 음소결정트리 기반 SSS 알고리즘(Phonetic Decision Tree-based Successive State Splitting： PDT-555)을 이용하였다 PDT-SSS 알고리즘은 미지의 문맥정보를 해결하기 위해 문맥방향과 시간방향으로 목표 상태수에 도달할 때까지 상태분할을 수행하여 모델을 작성하는 방법이다. 본 연구에서 강건한 문맥의존 음향모델을 학습하기 위한 방법의 유효성을 확인하기 위해 국어공학센터의 452 단어를 대상으로 음소와 단어인식 실험을 수행하였다. 실험결과, 음성의 시간변이에 따른 모델의 상태수와 각 음소의 문맥환경에 따라 인식성능의 변화를 고찰할 수 있었다. 따라서 본 연구는 향후 음성인식 시스템의 강건한 문맥의존 음향모델을 작성하는데 유효할 것으로 기대된다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.229-231
• /
• 2003

일반적으로 음성은 시간함수로 표현되며 음성인식에서 표준모델을 모델링하는 것은 매우 중요한 문제이다. 음절 단어, 연속음성을 발성할 때 자음과 모음에 따라 발성시간에 차이가 있으며 이를 잘 모델링하는 것 또한 음성인식에서는 중요한 문제라고 할 수 있다. 따라서 본 연구에서는 강건한 음향모델을 학습하기 위해 시간의 변화와 상태분할과정에서의 모델의 변화를 고려하여 다양한 구조의 초기모델을 작성하였다. 각 초기모델에 의한 HM-Net 문맥의존 음향모델은 음소결정트리 기반 SSS 알고리즘(PDT-SSS)을 이용하였다. PDT-SSS 알고리즘은 미지의 문맥정보를 해결하기 위해 문맥방향과 시간방향으로 목표 상태수에 도달할 때까지 상태분할을 수행하여 모델을 작성하는 방법이다. 음성의 시간변이를 고려한 강건한 문맥의존 음향모델을 작성하기 위해 설정한 각 모델의 구조에 대한 유효성을 확인하기 위해 국어공학센터의 452 단어를 대상으로 음소와 단어인식 실험을 수행한 결과. 음소인식의 경우 상태수 2000개에서 2상태 구조의 모델에 비해 4상태 구조가 약 11.4% 향상된 인식성능과 39.2초의 인식시간을 단축할 수 있었다. 또한 단어인식의 경우 상태수 2000개에서 1상태 구조의 모델에 비해 4상태 구조가 약 5% 향상된 인식성능과 4상태 구조에서 한 단어를 인식하는데 평균 0.8초가 소요되었다. 따라서 강건한 문맥의존 음향모델을 작성하기 위해 수행한 초기모델의 구조에 관한 연구가 향후 음성인식 시스템을 구축하는데 유효함을 확인할 수 있었다.

• 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.21 no.2
• /
• pp.199-210
• /
• 2002

In this paper, we carried out the study on speech recognition using the KM-Net topology design algorithm based on decision tree state-clustering to improve the performance of acoustic models in speech recognition. The Korean has many allophonic and grammatical rules compared to other languages, so we investigate the allophonic variations, which defined the Korean phonetics, and construct the phoneme question set for phonetic decision tree. The basic idea of the HM-Net topology design algorithm is that it has the basic structure of SSS (Successive State Splitting) algorithm and split again the states of the context-dependent acoustic models pre-constructed. That is, it have generated. the phonetic decision tree using the phoneme question sets each the state of models, and have iteratively trained the state sequence of the context-dependent acoustic models using the PDT-SSS (Phonetic Decision Tree-based SSS) algorithm. To verify the effectiveness of the above algorithm we carried out the speech recognition experiments for 452 words of center for Korean language Engineering (KLE452) and 200 sentences of air flight reservation task (YNU200). Experimental results show that the recognition accuracy has progressively improved according to the number of states variations after perform the splitting of states in the phoneme, word and continuous speech recognition experiments respectively. Through the experiments, we have got the average 71.5%, 99.2% of the phoneme, word recognition accuracy when the state number is 2,000, respectively and the average 91.6% of the continuous speech recognition accuracy when the state number is 800. Also we haute carried out the word recognition experiments using the HTK (HMM Too1kit) which is performed the state tying, compared to share the parameters of the HM-Net topology design algorithm. In word recognition experiments, the HM-Net topology design algorithm has an average of 4.0% higher recognition accuracy than the context-dependent acoustic models generated by the HTK implying the effectiveness of it.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.388-402
• /
• 2003

In this paper, we carried out the word, 4 continuous digits. continuous, and task-independent word recognition experiments to verify the effectiveness of the re-defined phoneme-likely units (PLUs) for the phonetic decision tree based HM-Net (Hidden Markov Network) context-dependent (CD) acoustic modeling in Korean appropriately. In case of the 48 PLUs, the phonemes /ㅂ/, /ㄷ/, /ㄱ/ are separated by initial sound, medial vowel, final consonant, and the consonants /ㄹ/, /ㅈ/, /ㅎ/ are also separated by initial sound, final consonant according to the position of syllable, word, and sentence, respectively. In this paper. therefore, we re-define the 39 PLUs by unifying the one phoneme in the separated initial sound, medial vowel, and final consonant of the 48 PLUs to construct the CD acoustic models effectively. Through the experimental results using the re-defined 39 PLUs, in word recognition experiments with the context-independent (CI) acoustic models, the 48 PLUs has an average of 7.06%, higher recognition accuracy than the 39 PLUs used. But in the speaker-independent word recognition experiments with the CD acoustic models, the 39 PLUs has an average of 0.61% better recognition accuracy than the 48 PLUs used. In the 4 continuous digits recognition experiments with the liaison phenomena. the 39 PLUs has also an average of 6.55% higher recognition accuracy. And then, in continuous speech recognition experiments, the 39 PLUs has an average of 15.08% better recognition accuracy than the 48 PLUs used too. Finally, though the 48, 39 PLUs have the lower recognition accuracy, the 39 PLUs has an average of 1.17% higher recognition characteristic than the 48 PLUs used in the task-independent word recognition experiments according to the unknown contextual factor. Through the above experiments, we verified the effectiveness of the re-defined 39 PLUs compared to the 48PLUs to construct the CD acoustic models in this paper.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2443-2446
• /
• 2003

본 논문에서는 한국전자통신연구원에서 제공된 대어휘 음성DB를 이용하여 HM-Net(Hidden Markov Network) 음성인식 시스템의 성능평가를 수행하였다. 음향모델 작성은 음성인식에서 널리 사용되고 있는 통계적인 모델링 방법인 HMM(Hidden Markov Model)을 개량한 HM-Net을 도입하였다 HM-Net은 PDT-SSS 알고리즘에 의해 문맥방향과 시간방향의 상태분할을 수행하여 생성되는데, 특히 문맥방향 상태분할의 경우 학습 음성데이터에 출현하지 않는 문맥정보를 효과적으로 표현하기 위해 음소결정트리를 채용하고 있으며, 시간방향 상태분할의 경우 학습 음성데이터에서 각 음소별 지속시간 정보를 효과적으로 표현하기 위한 상태분할을 수행한다. 이러한 상태분할을 수행하여 파라미터를 공유하게 되며 최적인 모델 네트워크를 작성하게 된다. 대어휘 음성데이터를 이용하여 음향모델을 작성하고 인식실험을 수행한 결과, 100명의 100단어와 60문장에 대해 평균 97.5％, 96.7％의 인식률을 보였다.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.397-400
• /
• 2003

본 연구에서는 KM-Net(Hidden Markov Network)을 다양한 태스크에의 적용과 화자의 특성을 효과적으로 나타내기 위해 HM-Net 음성인식 시스템에 MLLR(Maximum Likelihood Linear Regression) 적응방법을 도입하였으며, HM-Net 학습 알고리즘을 개량하여 회귀클래스 생성방법을 제안한다. 제안방법은 PDT-SSS(Phonetic Decision Tree-based Successive State Splitting) 알고리즘의 문맥방향 상태분할에 의한 상태레벨 공유를 이용한 방법으로 새로운 화자로부터 문맥정보와 적응화 데이터의 발성 양에 의존하여 결정된 많은 적응 파라미터들을(평균, 분산) 자유롭게 제어할 수 있게 된다. 제안방법의 유효성을 확인하기 위해 국어공학센터(KLE) 452 음성 데이터와 항공편 예약관련 연속음성을 대상으로 인식실험을 수행한 결과, 전체적으로 음소인식의 경우 평균 34-37％, 단어인식의 경우 평균 9％, 연속음성인식의 경우 평균 7-8％의 인식성능 향상을 각각 보였다. 또한 적응화 데이터의 양에 따른 인식성능 비교에서, 제안방법을 적용한 인식 시스템이 적응 데이터의 양이 적은 경우에도 향상된 인식률을 보였으며. 잡음을 부가한 음성에 대한 적응화 실험에서도 향상된 인식성능을 보여 MLLR 적응방법의 특성을 만족하였다. 따라서 MLLR 적응방법을 도입한 HM-Net 음성인식 시스템에 제안한 회귀클래스 생성방법이 유효함을 확인한 수 있었다.