#speech-recognition

Chinese search engine giant Baidu says it has developed a speech recognition system, called Deep Speech, the likes of which has never been seen, especially in noisy environments. In restaurant settings and other loud places where other commercial speech recognition systems fail, the deep learning model proved accurate nearly 81 percent of the time.

Are there some open source alternatives to what Wit.ai does, i.e. mapping voice/text queries to actions by defining recognition patterns? (Wit.ai has an open API, but source code is closed, making it inappropriate for education purposes.)

Fix: Speech recognition – MP3 to text software #dev #answer #computers

Speech recognition – MP3 to text software

I’m looking for a speaker independent program (commercial or free) that would enable me to transcribe MP3 files containing speech recordings (especially podcasts) to text. I wanted to try Dragon Naturally Speaking, but it seems like it only supports transcribing my own speech recordings. So what are the alternatives?

Answer [by Zach]: Speech recognition…

Facebook Acquires Speech-Recognition startup Mobile Technologies

Facebook announced that it has acquired Mobile Technologies,a leading speech recognition company. 

  Facebook product manager Tom Stocky announced the acquisition via Facebook.He said, “I’m excited to announce that we’ve agreed to acquire Mobile Technologies, a company with an amazing team that’s behind some of the world’s leading speech recognition and machine translation technology.

Mobile Technologies said on its website, “Facebook, with its mission to make the world more open and connected, provides the perfect platform to apply our technology at a truly global scale.

Voice recognition systems invoke concepts from a variety of fields including speech production, algebra, probability and statistics, information theory, linguistics, and various aspects of computer science. Voice recognition has therefore largely been viewed as an advanced science, typically meant for students and researchers who possess the requisite background and motivation.

This post describes techniques for turning the contents of Wikipedia into a set of sentences and a vocabulary suitable for use with language modelling toolkits or other applications.