• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1212-1215
• /
• 2017

현재 출시되는 AI스피커들의 기능들을 재현하면서 문제점을 찾아서 보완하고 특히 우리나라 1인 가구의 급격한 증가로 인한 다양한 사회 문제들의 해소 방안으로 표정인식을 통해 먼저 사용자에게 다가가는 감정적인 대화가 가능한 인공지능 서비스와 인터넷 환경에 무관한 홈 IoT 제어 그리고 시각데이터 제공이 가능한 다중 AI 스피커를 제작 하였다.

• Journal of Biomedical Engineering Research
• /
• v.23 no.6
• /
• pp.459-465
• /
• 2002

The goat of the present research is to improve the quality of life of both the elderly patients with dementia and their caregivers. For this Purpose, we developed a communication aid system that is consisted of three modules such as speech recognition engine, graphical agent. and database classified by a nursing schedule. The system was evaluated in an actual environment of nursing facility by introducing the system to an older mail patient with dementia. The comparison study was then carried out with and without system, respectively. The occupational therapists then evaluated subject"s reaction to the system by photographing his behaviors. The evaluation results revealed that the proposed system was more responsive in catering to needs of subject than professional caregivers. Moreover we could see that the frequency of causing the utterances of subject increased by introducing the system.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.675-681
• /
• 2021

With the recent growth of the AI speaker market, the demand for speech synthesis technology that enables natural conversation with users is increasing. Therefore, there is a need for a multi-speaker speech synthesis system that can generate voices of various tones. In order to synthesize natural speech, it is required to train with a large-capacity. high-quality speech DB. However, it is very difficult in terms of recording time and cost to collect a high-quality, large-capacity speech database uttered by many speakers. Therefore, it is necessary to train the speech synthesis system using the speech DB of a very large number of speakers with a small amount of training data for each speaker, and a technique for naturally expressing the tone and rhyme of multiple speakers is required. In this paper, we propose a technology for constructing a speaker encoder by applying the deep learning-based x-vector technique used in speaker recognition technology, and synthesizing a new speaker's tone with a small amount of data through the speaker encoder. In the multi-speaker speech synthesis system, the module for synthesizing mel-spectrogram from input text is composed of Tacotron2, and the vocoder generating synthesized speech consists of WaveNet with mixture of logistic distributions applied. The x-vector extracted from the trained speaker embedding neural networks is added to Tacotron2 as an input to express the desired speaker's tone.