• The Journal of the Acoustical Society of Korea
• /
• v.19 no.4
• /
• pp.31-36
• /
• 2000

This paper describes the implementation and the evaluation of the speech recognition automatic exchange system. The system provides government or public offices, companies, educational institutions that are composed of large number of members and parts with exchange service using speech recognition technology. The recognizer of the system is a Speaker-Independent, Isolated-word, Flexible-Vocabulary recognizer based on SCHMM(Semi-Continuous Hidden Markov Model). For real-time implementation, DSP TMS320C32 made in Texas Instrument Inc. is used. The system operating terminal including the diagnosis of speech recognition DSP and the alternation of speech recognition candidates makes operation easy. In this experiment, 8 speakers pronounced words of 1,300 vocabulary related to automatic exchange system over wire telephone network and the recognition system achieved 91.5% of word accuracy.

• The Magazine of the IEIE
• /
• v.28 no.4
• /
• pp.104-104
• /
• 2001

• MALSORI
• /
• no.67
• /
• pp.149-166
• /
• 2008

In spoken document retrievals (SDR), subword (typically phonemes) indexing term is used to avoid the out-of-vocabulary (OOV) problem. It makes the indexing and retrieval process independent from any vocabulary. It also requires a small corpus to train the acoustic model. However, subword indexing term approach has a major drawback. It shows higher word error rates than the large vocabulary continuous speech recognition (LVCSR) system. In this paper, we propose an probabilistic slot detection and n-gram based string matching method for phone based spoken document retrievals to overcome high error rates of phone recognizer. Experimental results have shown 9.25% relative improvement in the mean average precision (mAP) with 1.7 times speed up in comparison with the baseline system.

• 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.15 no.4E
• /
• pp.28-36
• /
• 1996

In this paper, we propose a new evaluation methodology which can more clearly show the performance of the allophone modeling algorithm generally used in large vocabulary speech recognition. The proposed evaluation method shows the running characteristics and limitations of the modeling algorithm by testing how the variation of phonetic environments of training data affects the recognition performance and the desirable number of free parameters to be estimated. Using the method, we experiment results, we conclude that, in vocabulary-independent recognition task, the phonetic diversity of training data greatly affects the robustness of model, and it is necessary to develop a proper measure which can determine the number of states compromizing the robustness and the precision of the HMnet better than the conventional modeling efficiency.

• Journal of Digital Convergence
• /
• v.11 no.9
• /
• pp.153-158
• /
• 2013

Target learning model is not recognized in this category or not classified clearly failed to determine if the vocabulary recognition is reduced. Form of classification learning model is changed or a new learning model is added to the recognition decision tree structure of the model should be changed to a structural problem. In order to solve these problems, a decision tree learning model for classification learning algorithm is proposed. Phonological phenomenon reflected sound enough to configure the database to ensure learning a decision tree learning model for classifying method was used. In this study, the indoor environment-dependent recognition and vocabulary words for the experimental results independent recognition vocabulary of the indoor environment-dependent recognition performance of 98.3% in the experiment showed, vocabulary independent recognition performance of 98.4% in the experiment shown.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.8
• /
• pp.3-8
• /
• 1999

Previous variable vocabulary speech recognition systems with context-independent acoustic modeling, could not represent the effect of neighboring phonemes. To solve this problem, we use allophone-based context-dependent acoustic model. This paper describes the method to improve acoustic model of the system effectively. Acoustic model is improved by using allophone clustering technique that uses entropy as a similarity measure and the optimal allophone model is generated by changing the number of allophones. We evaluate performance of the improved system by using Phonetically Optimized Words(POW) DB and PC commands(PC) DB. As a result, the allophone model composed of six hundreds allophones improved the recognition rate by 13% from the original context independent model m POW test DB.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.369-372
• /
• 1998

본 논문은 어휘독립(Vocabulary-Independent) 환경에서 별도의 훈련과정 없이 인식대상 어휘를 추가 및 변경할 수 있는 가변어휘(Variable Vocabulary) 음성인식에 관한 연구를 다룬다. 가변어휘 인식은 처음에 대용량 음성 데이터베이스(DB)로 음소모델을 훈련하고 인식대상 어휘가 결정되면 발음사전에 의거하여 음소모델을 연결함으로써 별도의 훈련과정 없이 인식대상 어휘를 변경 및 추가할 수 있다. 문맥 종속형(Context-Dependent) 음소 모델인 triphone을 사용하여 인식실험을 하였고, 인식성능의 비교를 위해 어휘종속 모델을 별도로 구성하여 인식실험을 하였다. Unseen triphone 문제와 훈련 DB의 부족으로 인한 모델 파라메터의 신뢰성 저하를 방지하기 위해 state-tying 방법 중 음성학적 지식에 기반을 둔 tree-based clustering(TBC) 기법[1]을 도입하였다. Mel Frequency Cepstrum Coefficient(MFCC)와 대수에너지에 기반을 둔 3 가지 음성특징 벡터를 사용하여 인식 실험을 병행하였고, 연속 확률분포를 가지는 Hidden Markov Model(HMM) 기반의 고립단어 인식시스템을 구현하였다. 인식 실험에는 22 개 부서명 DB[3]를 사용하였다. 실험결과 어휘독립 환경에서 최고 98.4%의 인식률이 얻어졌으며, 어휘종속 환경에서의 인식률 99.7%에 근접한 성능을 보였다.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2E
• /
• pp.66-71
• /
• 2009

In practical applications of speech recognition, one of the fundamental questions might be on the number of training data that should be provided for a specific task. Though plenty of training data would undoubtedly enhance the system performance, we are then faced with the problem of heavy cost. Therefore, it is of crucial importance to determine the least number of training data that will afford a certain level of accuracy. For this purpose, we investigate the effect of the number of training data on the speaker-independent speech recognition of isolated words by using FVQ/HMM. The result showed that the error rate is roughly inversely proportional to the number of training data and grows linearly with the vocabulary size.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3E
• /
• pp.19-23
• /
• 1997

The goal of postprocessing in automatic speech recognition is to improve recognition performance by utterance verification at the output of recognition stage. It is focused on the effective rejection of out-of vocabulary words based on the confidence score of hypothesized candidate word. We present two methods for computing confidence scores. Both methods are based on the distance between each observation vector and the representative code vector, which is defined by the most likely code vector at each state. While the first method employs simple time normalization, the second one uses a normalization technique based on the concept of on-line garbage mode[1]. According to the speaker independent isolated words recognition experiment with discrete density HMM, the second method outperforms both the first one and conventional likelihood ratio scoring method[2].