• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.7-10
• /
• 1999

본 논문에서는 logatom 기반 무제한 한국어 TTS 시스템 구현을 제안한다. 이를 위하여 한국어를 대표할 만한 문서코퍼스를 선택하여 분석하고 이를 바탕으로 합성에 필요한 logatom을 설계한다. 일반적으로 음성코퍼스를 통해 음성세그먼트를 추출하여 접속에 기반한 TTS 시스템에서는 음성세그먼트를 의미있는 단어 또 는 어절로부터 추출한다. 하지만 음성세그먼트 추출시 고려되는 사항은 합성단위에 기초한 음소간의 결합형태이므로 본 논문에서는 음성세그먼트 추출을 위하여 무의미한 음소열인 logatom을 설계한다. Logatom은 문장 세그먼트의 어절내 위치와 문서코퍼스 분석 결과 얻어진 음소간의 결합형태를 기반으로 설계된다. 제안된 시스템의 합성음질을 평가하기 위하여 CVC 기반 logatom을 사용하여 임의의 문장을 합성해 본 결과 대부분의 음성세그먼트 접속이 자음에서 이루어지고 어절의 위치를 고려한 logatom 설계로 인하여 어절 내에서는 비교적 자연스러운 합성음을 얻을 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.703-710
• /
• 2003

Because of their human-like synthesized speech quality, recently Corpus-Based Text-To-Speech(CB-TTS) have been actively studied worldwide. However, due to their large size speech database (DB), their application is very restricted. In this paper we propose and evaluate three DB reduction algorithms to which are designed to solve the above drawback. The first method is based on a K-means clustering approach, which selects k-representatives among multiple instances. The second method is keeping only those unit instances that are selected during synthesis, using a domain-restricted text as input to the synthesizer. The third method is a kind of hybrid approach of the above two methods and is using a large text as input in the system. After synthesizing the given sentences, the used unit instances and their occurrence information is extracted. As next step a modified K-means clustering is applied, which takes into account also the occurrence information of the selected unit instances, Finally we compare three pruning methods by evaluating the synthesized speech quality for the similar DB reduction rate, Based on perceptual listening tests, we concluded that the last method shows the best performance among three algorithms. More than this, the results show that the last method is able to reduce DB size without speech quality looses.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.3
• /
• pp.209-215
• /
• 2010

Recently portable terminal is received attention by wireless networks and mass capacity ROM. In this result, TTS(Text to Speech) system is inserted to portable terminal. Nevertheless high quality synthesis is difficult in portable terminal, users need high quality synthesis. In this paper, we proposed Distributed TTS (DTTS) that was composed of server and terminal. The DTTS on corpus based speech synthesis can be high quality synthesis. Synthesis system in server that generate optimized speech concatenation information after database search and transmit terminal. Synthesis system in terminal make high quality speech synthesis as low computation using transmitted speech concatenation information from server. The proposed method that can be reducing complexity, smaller power consumption and efficient maintenance.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.87-90
• /
• 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, i.e. a dictionary-based and rule-based hybrid method, for unlimited vocabulary Korean TTS. We constructed a prosody model using a probabilistic method and decision tree-based method.

• Proceedings of the KSPS conference
• /
• 2003.10a
• /
• pp.175-179
• /
• 2003

In order to produce a high quality (intelligibility and naturalness) synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model. In this paper, we analyzed Chinese texts using a segmentation, POS tagging and unknown word recognition. We present a grapheme-to-phoneme conversion using a dictionary-based and rule-based method. We constructed a prosody model using a probabilistic method and a decision tree-based error correction method. According to the result from the above analysis, we can successfully select and concatenate exact synthesis unit of syllables from the Chinese Synthesis DB.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.359-366
• /
• 2022

In this paper, we present the Korean menu-ordering Sentence Text-to-Speech (TTS) system using conformer-based FastSpeech2. Conformer is the convolution-augmented transformer, which was originally proposed in Speech Recognition. Combining two different structures, the Conformer extracts better local and global features. It comprises two half Feed Forward module at the front and the end, sandwiching the Multi-Head Self-Attention module and Convolution module. We introduce the Conformer in Korean TTS, as we know it works well in Korean Speech Recognition. For comparison between transformer-based TTS model and Conformer-based one, we train FastSpeech2 and Conformer-based FastSpeech2. We collected a phoneme-balanced data set and used this for training our models. This corpus comprises not only general conversation, but also menu-ordering conversation consisting mainly of loanwords. This data set is the solution to the current Korean TTS model's degradation in loanwords. As a result of generating a synthesized sound using ParallelWave Gan, the Conformer-based FastSpeech2 achieved superior performance of MOS 4.04. We confirm that the model performance improved when the same structure was changed from transformer to Conformer in the Korean TTS.

• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.77-83
• /
• 2012

본 연구에서는 로봇의 자동 동화구연을 목표로 발화문장 상의 감정 파악 및 등장인물 별 다앙한 TTS 보이스 선택에 활용 가능한 발화문장의 화자 파악문제를 다룬다. 본 연구에서는 기존 규칙기반 방법론에서 많이 활용되어온 자질인 후보의 위치, 화자 후보의 주격/목적격 여부, 발화동사 존재 여부를 비롯하여 동화에 자주 나타나는 등장인물의 의미적 분류 및 등장인물의 등장/퇴장과 관련된 동사들을 추가 자질로 활용한다. 사람 및 동식물, 무생물이 모두 화자가 될 수 있는 동화 코퍼스에서 제안한 자질들을 활용하여 의사결정트리로 학습 및 검증한 결과 규칙기반의 베이스라인 방법에 비해 최대 49%의 정확도가 향상되었고, 제안한 방법론이 데이터의 변화에도 강인한 것을 확인할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.285-292
• /
• 2002

One of the problems that should be solved in Text-To-Speech (TTS) is discontinuities at unit-joining points. To cope with this problem, a smoothing method using a low-pass filter is employed in this paper, In the proposed soothing method, a filter coefficient that controls the amount of smoothing is determined according to contort information to be synthesized. This method efficiently reduces both discontinuities at unit-joining points and artifacts caused by undesired smoothing. The amount of smoothing is determined with discontinuities around unit-joins points in the current synthesized speech and discontinuities predicted from context. The discontinuity predictor is implemented by CART that has context feature variables. To evaluate the performance of the proposed method, a corpus-based concatenative TTS was used as a baseline system. More than 6075 of listeners realized that the quality of the synthesized speech through the proposed smoothing is superior to that of non-smoothing synthesized speech in both naturalness and intelligibility.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.8
• /
• pp.403-408
• /
• 2007

In a large corpus-based speech synthesizer, a break, which is a parameter influencing the naturalness and intelligibility, is used as an important feature during a unit selection process. Japanese is a language having intonations, which ate indicated by the relative differences in pitch heights and the APs(Accentual Phrases) are placed according to the changes of the accents while a break occurs on a boundary of the APs. Although a break can be predicted by using J-ToBI(Japanese-Tones and Break Indices), which is a rule-based or statistical approach, it is very difficult to predict a break exactly due to the flexibility. Therefore, in this paper, a method is to conduct a unit search by dividing breaks into two types, such as a fixed break and a flexible break, in order to use the advantages of a large-scale corpus, which includes various types of prosodies. As a result of an experiment, the proposed unit selection method contributed itself to enhance the naturalness of synthesized speeches.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.84-88
• /
• 1999

The accurate estimation of segmental duration is crucial for natural-sounding text-to-speech synthesis. For predicting Korean segmental durations, conventional methods utilized phonemic context, part-of-speech context and locational information in prosodic phrase. In this paper, the tonal information of phonemes is employed for more accurate prediction. After defining two non-boundary tones and six boundary tones, we annotated the tonal label on each syllable of 400 sentences. To predict segmental duration using tonal information, we constructed neural networks with a real-valued output node predicting phonemic duration and trained them by backpropagation algorithm. Experimental results showed that the proposed features are effective for predicting Korean segmental durations, and we got 0.863 correlation coefficient of the observed durations and predicted ones.