Sony Working on Improving Voice Recognition for PlayStation Games for Current and Future Platforms
Sony Computer Entertainment America just posted a quite interesting career opportunity ad, seeking a Software Engineer for its R&D department.
The candidate will work on “the voice recognition SDK development for PlayStation games for current and future platforms.” What’s even more interesting is that it lists in detail the purposes of said research, and the improvements the company is looking to accomplish:
*To implement, improve and handle CSR language modeling and automatic pronunciation generation for multiple languages
* To improve voice recognition accuracy and out-of-vocabulary rejection rate for noisy speech, kid’s speech, and emotional speech with limited CPU and memory for multi languages
* Improve runtime voice recognition and sample voice applications for PlayStation product for many languages
* Develop robust automatic speech recognition (ASR) technologies to various kinds of distortions and variations such as channel and environment distortions, emotional speech, variety of speaking rate and speaking style for multiple languages
* Integrate ASR with technologies of microphone array, echo cancellation, speech enhancement, and other DSP processing for far-field voice recognition under noise
* Implement and improve very large vocabulary continuous voice recognition performance under variety of game sounds and music background
* Improve acoustic model training and adaptation
While Sony did not forcefully include the PlayStation Camera with in the PS4’s box like Microsoft did with Kinect and the Xbox One, looks like research is continuing to be competitive in the voice recognition field applied to gaming. We’ll have to wait and see the results, but it’s definitely intriguing.