• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2431-2434
• /
• 2003

In this research, our goal is to realize Korean Distribute TTS system with server/client function in wireless network. The speech databases and some routines of TTS system is stuck with the server which has strong functions and we made Korean speech databases and accomplished research about DB which is suitable for distributed TTS. We designed a terminal has the minimum setting which operate this TTS and designed proper protocol so we will check action of Distributed TTS.

• MALSORI
• /
• no.53
• /
• pp.75-92
• /
• 2005

Prosody Generation Based on C-ToBI Representation for Text-to-SpeechSeungwon Kim, Yu Zheng, Gary Geunbae Lee, Byeongchang KimProsody modeling is critical in developing text-to-speech (TTS) systems where speech synthesis is used to automatically generate natural speech. In this paper, we present a prosody generation architecture based on Chinese Tone and Break Index (C-ToBI) representation. ToBI is a multi-tier representation system based on linguistic knowledge to transcribe events in an utterance. The TTS system which adopts ToBI as an intermediate representation is known to exhibit higher flexibility, modularity and domain/task portability compared with the direct prosody generation TTS systems. However, the cost of corpus preparation is very expensive for practical-level performance because the ToBI labeled corpus has been manually constructed by many prosody experts and normally requires a large amount of data for accurate statistical prosody modeling. This paper proposes a new method which transcribes the C-ToBI labels automatically in Chinese speech. We model Chinese prosody generation as a classification problem and apply conditional Maximum Entropy (ME) classification to this problem. We empirically verify the usefulness of various natural language and phonology features to make well-integrated features for ME framework.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.640-645
• /
• 2021

The deep learning based end-to-end TTS system consists of Text2Mel module that generates spectrogram from text, and vocoder module that synthesizes speech signals from spectrogram. Recently, by applying deep learning technology to the TTS system the intelligibility and naturalness of the synthesized speech is as improved as human vocalization. However, it has the disadvantage that the inference speed for synthesizing speech is very slow compared to the conventional method. The inference speed can be improved by applying the non-autoregressive method which can generate speech samples in parallel independent of previously generated samples. In this paper, we introduce FastSpeech, FastSpeech 2, and FastPitch as Text2Mel technology, and Parallel WaveGAN, Multi-band MelGAN, and WaveGlow as vocoder technology applying non-autoregressive method. And we implement them to verify whether it can be processed in real time. Experimental results show that by the obtained RTF all the presented methods are sufficiently capable of real-time processing. And it can be seen that the size of the learned model is about tens to hundreds of megabytes except WaveGlow, and it can be applied to the embedded environment where the memory is limited.

• Phonetics and Speech Sciences
• /
• v.13 no.4
• /
• pp.47-53
• /
• 2021

Autoregressive Text-to-Speech (TTS) models suffer from inference instability and slow inference speed. Inference instability occurs when a poorly predicted sample at time step t affects all the subsequent predictions. Slow inference speed arises from a model structure that forces the predicted samples from time steps 1 to t-1 to predict the sample at time step t. In this study, an end-to-end non-autoregressive fast text-to-speech model is suggested as a solution to these problems. The results of this study show that this model's Mean Opinion Score (MOS) is close to that of Tacotron 2 - WaveNet, while this model's inference speed and stability are higher than those of Tacotron 2 - WaveNet. Further, this study aims to offer insight into the improvement of non-autoregressive models.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.619-620
• /
• 2019

기존의 TTS (Text to Speech) 기술이 가지고 있는 음질의 한계를 GAN - Super Resolution 기술을 이용하여 개선시킨다.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.167-177
• /
• 2003

This paper presents a method of building an exceptional pronunciation dictionary for Korean automatic pronunciation generator. An automatic pronunciation generator is an essential element of speech recognition system and a TTS (Text-To-Speech) system. It is composed of a part of regular rules and an exceptional pronunciation dictionary. The exceptional pronunciation dictionary is created by extracting the words which have exceptional pronunciations from text corpus based on the characteristics of the words of exceptional pronunciation through phonological research and text analysis. Thus, the method contributes to improve performance of Korean automatic pronunciation generator as well as the performance of speech recognition system and TTS system.

• MALSORI
• /
• no.48
• /
• pp.57-67
• /
• 2003

This paper presents a systematic description of exceptional pronunciations for automatic Korean pronunciation generation. An automatic pronunciation generator in Korean is an essential part of a Korean speech recognition system and a TTS (Text-To-Speech) system. It is composed of a set of regular rules and an exceptional pronunciation dictionary. The exceptional pronunciation dictionary is created by extracting the words that have exceptional pronunciations, based on the characteristics of the words of exceptional pronunciation through phonological research and the systematic analysis of the entries of Korean dictionaries. Thus, the method contributes to improve performance of automatic pronunciation generator in Korean as well as the performance of speech recognition system and TTS system in Korean.

• Phonetics and Speech Sciences
• /
• v.11 no.2
• /
• pp.57-64
• /
• 2019

In this paper, we construct a Korean text-to-speech system using the Merlin toolkit which is an open source system for speech synthesis. In the text-to-speech system, the HMM-based statistical parametric speech synthesis method is widely used, but it is known that the quality of synthesized speech is degraded due to limitations of the acoustic modeling scheme that includes context factors. In this paper, we propose an acoustic modeling architecture that uses deep neural network technique, which shows excellent performance in various fields. Fully connected deep feedforward neural network (DNN), recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional LSTM (BLSTM) are included in the architecture. Experimental results have shown that the performance is improved by including sequence modeling in the architecture, and the architecture with LSTM or BLSTM shows the best performance. It has been also found that inclusion of delta and delta-delta components in the acoustic feature parameters is advantageous for performance improvement.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.148-155
• /
• 2020

This study investigated learners' perceptions of using self-generated listening materials based on Text to Speech. After taking an online training session to learn how to make listening materials for extensive listening practice outside the classroom, the learners were engaged in practice with self-generated listening materials for 10 weeks in a self-directed way. The results show that a majority of the learners found the TTS-based listening materials helpful to reduce anxiety toward listening and enhance self-confidence and motivation, with a positive effect on improving their listening ability. The learners' general satisfaction can be attributed to some beneficial features of TTS-based listening material, including freedom to choose what they want to learn, convenient accessibility to the material, availability of various native speakers' voices, and novelty of digital tools. This suggests that TTS-based digital listening materials can be a useful educational tool to support learners' self-directed listening practice outside the classroom in EFL settings.

• 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.