Use the Iflytek SDK to realize speech recognition-semantic recognition and other functions on Ubuntu

First, refer to the case of official SDK to realize the daily dialogue and control of the machine.

Specific steps:

1. Capture the spoken sound through the microphone, and then get the characters in the voice through online speech recognition.

2. Upload the acquired characters to the semantic recognition of  and get back the information. (JSON format)

3. Parse the returned data through the Cjson library to get the data we want.

4. Upload the obtained results to the  library for speech synthesis and get the synthesized voice data.

5. Output sound through the ALSA library.

The specific code has been uploaded to GitHub.

Https://github.com/qq2216691777/xf_voice

Use the  SDK to realize speech recognition-semantic recognition and other functions on Ubuntu