• 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.

• Speech Sciences
• /
• v.10 no.1
• /
• pp.71-84
• /
• 2003

In the acoustic modeling for large vocabulary speech recognition, a sparse data problem caused by a huge number of context-dependent (CD) models usually leads the estimated models to being unreliable. In this paper, we develop a new clustering method based on the C45 decision-tree learning algorithm that effectively encapsulates the CD modeling. The proposed scheme essentially constructs a supervised decision rule and applies over the pre-clustered triphones using the C45 algorithm, which is known to effectively search through the attributes of the training instances and extract the attribute that best separates the given examples. In particular, the data driven method is used as a clustering algorithm while its result is used as the learning target of the C45 algorithm. This scheme has been shown to be effective particularly over the database of low unknown-context ratio in terms of recognition performance. For speaker-independent, task-independent continuous speech recognition task, the proposed method reduced the percent accuracy WER by 3.93% compared to the existing rule-based methods.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.5
• /
• pp.24-31
• /
• 1994

In this paper, we study continuous speech recognition of Korean language using acoustic models of word juncture coarticulation. To alleviate the performance degradation due to coarticulation problems, we use context-dependent units that model inter-word transitions in addition to intra-word transitions. In all cases the initial phone of each word has to be specified for each possible final phone of the previous word similarly for the final phone of each word. To improve the robustness of the HMM parameters, the covariance matrix is smoothed. We also use position-dependent units to improve the discriminative power between units. Simulation results show that when the improved models of word juncture coarticulation are used. the recognition performance is considerably improved compared to the baseline system using only intra-word units.

• 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.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.1
• /
• pp.23-27
• /
• 2003

Recently attempts to we the syllable as the recognition unit to enhance performance in continuous speech recognition hate been reported. However, syllables are worse in their trainability than phones and the former have a disadvantage in that contort-dependent modeling is difficult across the syllable boundary since the number of models is much larger for syllables than for phones. In this paper, we propose a method to enhance the trainability for the syllables in Korean and phoneme-context dependent syllable modeling across the syllable boundary. An experiment in which the proposed method is applied to word recognition shows average 46.23% error reduction in comparison with the common syllable modeling. The right phone dependent syllable model showed 16.7% error reduction compared with a triphone model.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.49-56
• /
• 1999

In many continuous speech recognition systems based on HMMs, decision tree-based state tying has been used for not only improving the robustness and accuracy of context dependent acoustic modeling but also synthesizing unseen models. To construct the phonetic decision tree, standard method performs one-level pruning using just single Gaussian triphone models. In this paper, two novel approaches, two-level decision tree and multi-mixture decision tree, are proposed to get better performance through more accurate acoustic modeling. Two-level decision tree performs two level pruning for the state tying and the mixture weight tying. Using the second level, the tied states can have different mixture weights based on the similarities in their phonetic contexts. In the second approach, phonetic decision tree continues to be updated with training sequence, mixture splitting and re-estimation. Multi-mixture Gaussian as well as single Gaussian models are used to construct the multi-mixture decision tree. Continuous speech recognition experiment using these approaches on BN-96 and WSJ5k data showed a reduction in word error rate comparing to the standard decision tree based system given similar number of tied states.