By Beijing Kexin Technology Co.

Function Description

ThinkIT song selection by speech (S3) solution functions as a song selection system for KTV entertainment, either by selecting via speech, the name of a song or a singer, or by humming the melody, or by reading lyrics of a wanted song, the solution can also function as a singing scoring system in KTV rooms. Due to its simple use and easy switch over between operations, this solution is now being applied in KTV entertainment to replace the traditional song selection system.

Technical solutions

Figure 1 diagram for ThinkIT KTV song selection by speech solution

　　The diagram for ThinkIT KTV song selection by speech solution is shown above in Figure 1. The core technologies behind the ThinkIT S3 system are based on the speech processing platform developed by ThinkIT for several years, for telecommunication speech applications, i.e., the ThinkIT speech environment (TSE). TSE includes a speech recognition engine, a singing scoring engine, a music melody recognition engine, and a lyrics recognition engine. TSE provides a complete API function library, application examples and relevant documents, and can be conveniently integrated into application systems. The TSE is proven as a mature system and easy to use.
　　During song selection, speech signal is passed through the microphone into the control box, which switches between the modes of singing and song selection over the microphone. The switch command comes from the song selection terminal. When in the normal singing mode, the signal from the microphone directly enters the amplifier through the control box, and when in the song selection mode, the signal is diverted into the song selection machine where it will be digitalized and be further passed onto the recognition engine TSE located in the song selection server. The recognition result from the TSE with related status information will then be returned to the song selection machine.