• MALSORI
• /
• no.46
• /
• pp.51-64
• /
• 2003

In order to produce high quality synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model from texts using natural language processing. Robust preprocessing for non-Korean characters should also be required. In this paper, we analyzed Korean texts using a morphological analyzer, part-of-speech tagger and syntactic chunker. We present a new grapheme-to-phoneme conversion method for Korean using a hybrid method with a phonetic pattern dictionary and CCV (consonant vowel) LTS (letter to sound) rules, for unlimited vocabulary Korean TTS. We constructed a prosody model using a probabilistic method and decision tree-based method. The probabilistic method atone usually suffers from performance degradation due to inherent data sparseness problems. So we adopted tree-based error correction to overcome these training data limitations.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.288-291
• /
• 2007

The aim of this study is to clarify degrees of difficulty of the Japanese L2 (second language) learners for learning Korean sounds and phonological rules. 31 subjects took a questionnaire survey and an identification test using words. In addition, each subject's pronunciation was evaluated by 3 Korean native speakers. As for Korean sounds, the results show that Japanese L2 learners have a tendency perceiving that listening is more difficult than pronouncing, although the listening test's scores were greater than the pronunciation test's scores for a majority of the items. As for Korean phonological rules, 1) there were some difficult items for applying the phonological rules, although Japanese L2 learners had knowledge of them, and 2) there were also some items that Korean native speakers evaluated Japanese L2 learners' pronunciations as the phonological rules were applied, even though learners pronounced them without any knowledge.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.35-43
• /
• 2001

Many speech recognition systems have used pronunciation lexicon with possible multiple phonetic transcriptions for each word. The pronunciation lexicon is of often manually created. This process requires a lot of time and efforts, and furthermore, it is very difficult to maintain consistency of lexicon. To handle these problems, we present a model based on morphophon-ological analysis for automatically generating Korean pronunciation variants. By analyzing phonological variations frequently found in spoken Korean, we have derived about 700 phonemic contexts that would trigger the multilevel application of the corresponding phonological process, which consists of phonemic and allophonic rules. In generating pronunciation variants, morphological analysis is preceded to handle variations of phonological words. According to the morphological category, a set of tables reflecting phonemic context is looked up to generate pronunciation variants. Our experiments show that the proposed model produces mostly correct pronunciation variants of phonological words. Then we estimated how useful the pronunciation lexicon and training phonetic transcription using this proposed systems.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.201-203
• /
• 1999

음성합성에서 자연스러운 합성음을 생성하기 위하여 표준 발음법을 페트리넷 근저행렬로 모델링하는 방법으로 표준 발음법을 음가 생성 규칙으로 만들 수 있다. 본 논문은 페트리넷으로 모델링된 음가 생성 규칙의 크기를 줄이는 방법을 제안하고 구현하였다. 압축하기 전의 음가 생성 테이블의 크기는 719*107의 2차원 배열이었으며 구현된 시스템으로 압축한 결과 41*40의 2차원 구조체 배열로 압축되었다.

• MALSORI
• /
• no.56
• /
• pp.185-194
• /
• 2005

In this paper, we present POSSDM (POSTECH Situation-Based Dialogue Manager) for a spoken dialogue system using a new example and situation-based dialogue management technique for effective generation of appropriate system responses. Spoken dialogue system should generate cooperative responses to smoothly control dialogue flow with the users. We introduce a new dialogue management technique incorporating dialogue examples and situation-based rules for EPG (Electronic Program Guide) domain. For the system response inference, we automatically construct and index a dialogue example database from dialogue corpus, and the best dialogue example is retrieved for a proper system response with the query from a dialogue situation including a current user utterance, dialogue act, and discourse history. When dialogue corpus is not enough to cover the domain, we also apply manually constructed situation-based rules mainly for meta-level dialogue management.

• MALSORI
• /
• no.49
• /
• pp.107-121
• /
• 2004

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon to improve the performance of a Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished phonological rules that can be applied to phonemes in within-morpheme and cross-morpheme. The results of 33K-morpheme Korean CSR experiments show that an absolute reduction of 1.45% in WER from the baseline performance of 18.42% WER was achieved by modeling proposed pronunciation variations with a possible multiple context-dependent pronunciation lexicon.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• pp.113-115
• /
• 2005

In this paper, we present POSSDM (POSTECH Situation-Based Dialogue Manager) for a spoken dialogue system using a new example and situation-based dialogue management techniques for effective generation of appropriate system responses. Spoken dialogue system should generate cooperative responses to smoothly control dialogue flow with the users. We introduce a new dialogue management technique incorporating dialogue examples and situation-based rules for EPG (Electronic Program Guide) domain. For the system response inference, we automatically construct and index a dialogue example database from dialogue corpus, and the best dialogue example is retrieved for a proper system response with the query from a dialogue situation including a current user utterance, dialogue act, and discourse history. When dialogue corpus is not enough to cover the domain, we also apply manually constructed situation-based rules mainly for meta-level dialogue management.

• MALSORI
• /
• no.58
• /
• pp.67-81
• /
• 2006

For a large corpus of time-aligned data, HMM based approaches are most widely used for automatic segmentation, providing a consistent and accurate phone labeling scheme. There are two methods for training in HMM. Flat starting method has a property that human interference is minimized but it has low accuracy. Bootstrap method has a high accuracy, but it has a defect that manual segmentation is required In this paper, a new algorithm is proposed to minimize manual work and to improve the performance of automatic segmentation. At first phase, voiced, unvoiced and silence classification is performed for each speech data frame. At second phase, the phoneme sequence is aligned dynamically to the voiced/unvoiced/silence sequence according to the acoustic phonetic rules. Finally, using these segmented speech data as a bootstrap, phoneme model parameters based on HMM are trained. For the performance test, hand labeled ETRI speech DB was used. The experiment results showed that our algorithm achieved 10% improvement of segmentation accuracy within 20 ms tolerable error range. Especially for the unvoiced consonants, it showed 30% improvement.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.851-861
• /
• 1998

Korean language is to be characterized by the rich vocal sound variation. In order to increase the probability of vocal sound recognition and to provide a natural vocal sound synthesis, a systematic and thorough research into the characteristics of Korean language including its vocal sound changing rules is required. This paper addresses an effective way of vocal sound recognition and synthesis by providing the design and implementation of the Korean vocal sound variation rule. The regulation we followed for the design of the vocal sound variation rule is the Phonetic Standard(Section 30. Chapter 7) of the Korean Orthographic Standards. We have first factor out rules for each regulations, then grouped them into 27 groups for eaeh final-consonant. The Phonological Change Processing System suggested in the paper provides a fast processing ability for vocal sound variation by a single application of the rule. The contents of the process for information augmented to words or the stem of innected words are included in the rules. We believe that the Phonological Change Processing System will facilitate the vocal sound recognition and synthesis by the sentence. Also, this system may be referred as an example for similar research areas.

• 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.