카카오 i 엔진
음성엔진Kakao i Voice Engine
사람의 말소리를 분석하여 텍스트 문자열로 변환시키는 음성인식, 텍스트를 입력하면 자연스러운 사람의 목소리를 생성하는 음성합성 기능을 제공합니다. 특정 키워드에 반응하여 기기를 호출하고 등록된 사용자의 목소리를 구별할 수 있습니다.
- 음성합성 (TTS)
- 음성인식 (STT)
- 핵심어 검출
- 화자 인식
Publications
-
논문
JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment Interspeech 2020Dan Lim, Won Jang, Gyeonghwan O, Hyeyeong Park, Bongwan Kim, Jesam Yoon
-
논문
Affective Latent Representation of Acoustic and Lexical Features for Emotion Recognition MDPI 2020Eesung Kim, Hyungchan Song, Jong Won Shin
-
논문
Speech Enhancement Using a Two-stage Network For an Efficient Boosting Strategy ICASSP 2020Juntae Kim, Minsoo Hahn
-
논문
Many-To-Many Voice Conversion Using Conditional Cycle-Consistent Adversarial Networks ICASSP 2020Shindong Lee, BongGu Ko, Keonnyeong Lee, In-Chul Yoo, Dongsuk Yook
-
논문
DNN-based Emotion Recognition based on Bottleneck Acoustic Features and Lexical Features ICASSP 2019Eesung Kim, Jong Won Shin