SinoVoice’s Strato platform

Recently I am fond of how the technology of speaker recognition and some related technologies are going in China. SinoVoice company is the one that first attract my eyes.

SinoVoice Company is one of the earliest companies that do research on artificial intelligence technology. In particular, the speech recognition, speech synthesis, speaker recognition, natural language understanding technology are four core technologies to form a complete closed-loop intelligent voice technology ecosystem for their artificial intelligence platform named Strato.

I think SinoVoice is a very considerable company. They are the only company that has Uighur language speech recognition and speech synthesis, a language used by people from minority of China.

Another thing that I appreciate is that SinoVoice alliance with Tsinghua University, co-found the “Qing Hua Lingyun Artificial Intelligence Research Center” in 2013. Tsinghua University is the university that most of Chinese students who learn science or industry dreaming of to attend. Hence, I think SinoVoice has long-term vision and there are sure to make huge contribution in artificial intelligence technologies. In addition, the launch of the speaker recognition technology is one of the outstanding fruits of “Qing Hua Lingyun Artificial Intelligence Research Center “.

Are you also interested in the development of speaker recognition in China? Or do you already have some knowledge of how well this technology is developed in other countries all over the world? Feel free to contribute your idea here.

Source: http://news.sina.com.cn/o/2014-11-26/103631204884.shtml

http://www.sinovoice.com/english/index.html

Advertisements

2 comments

  1. mathiasder · March 10, 2015

    hello,

    I am very interested in speaker recognition all over the world. But is there a big difference between speaker recognition here and china? Cause the way of talking is different, no? In Chinese language they use more with pitches then here in Belgium? Doesn’t that make it harder or easier to recognition someone?

    Like

    • wumiaomiao201410 · March 10, 2015

      Hi,
      There exists text-independent speaker recognition, which makes no difference whether someone is speaking Chinese or Dutch. But if you want to do a recognition, you can first detect which language he is saying as a assistant to make the accuracy higher.

      Like

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s