GTCOM's intelligent speech technology platform employs mature multilingual speech recognition and synthesis technologies. It provides speech-interaction solutions in Chinese, English, Japanese, Korean, German and Portuguese for real-world speech-interaction scenarios.
Speech is the most natural, convenient means of man-machine interaction, and consequently it's important as a gateway to the next-generation man-machine interaction. GTCOM actively pursues the questions of form and layout in the field of speech. It has developed an internationally advanced speech-recognition technology based on a self-adaptive, context-dependent, deep-neural-network hidden Markov model. Moreover, it has applied deep convolutional neural network technology to acoustical modeling, combined with the end-to-end speech-recognition technology based on long short-term memory (LSTM) and connectionist temporal classification (CTC) in order to reduce the error rate and dramatically improve the performance of speech recognition.
Based on the large-scale, in-depth integration of high-quality corpora, GTCOM has built speech-recognition engines covering Chinese, English, Japanese, Korean, German and Portuguese through the use of its proprietary deep-learning technology framework, and each language is supported by more than 10,000 hours of corpora training. Its speech-recognition level remains the highest in the world. These accurate speech-recognition engines have been successfully used in GTCOM's language-technology products--including JoveTrans, the FindYee app and the YeeCloud Cloud input method--thus creating a solid foundation in the speech-recognition market. In the near future, GTCOM will expand its range of languages and provide speech-recognition solutions for users in many more languages so that people of all cultures and environments can exchange ideas.
For more information: RIDbusiness@gtcom.com.cn