Speech Recognition
19 views | +0 today
Follow
Your new post is loading...
Your new post is loading...
Scooped by Jochen Schwenninger
Scoop.it!

Inside Nuance: the art and science of how Siri speaks

Read the full feature here: http://www.theverge.com/2013/9/17/4596374/machine-language-how-siri-found-its-voice Clarification: Allison Dufty is not the voice...
more...
No comment yet.
Scooped by Jochen Schwenninger
Scoop.it!

Turn your Raspberry Pi into a Translator with Speech Recognition and Playback (60+ languages)

Turn your Raspberry Pi into a Translator with Speech Recognition and Playback (60+ languages) | Speech Recognition | Scoop.it
Turn your Raspberry Pi into a Translator with Speech Recognition and Playback (60+ languages) http://t.co/x5ZxUFNT3i
Jochen Schwenninger's insight:

For all the Raspberry Pi hackers out there...

more...
No comment yet.
Scooped by Jochen Schwenninger
Scoop.it!

Large Scale Language Modeling in Automatic Speech Recognition ...

As they say: there's no data like more data...

 

"At Google, we're able to use the large amounts of data made available by the Web's fast growth. Two such data sources are the anonymized queries on google.com and the web itself. They help improve automatic speech ..."

 

 

more...
No comment yet.
Scooped by Jochen Schwenninger
Scoop.it!

Speech Recognition Breakthrough for the Spoken, Translated Word

Chief Research Officer Rick Rashid demonstrates a speech recognition breakthrough via machine translation that converts his spoken English words into compute... (Keren #Microsoft Research!
more...
No comment yet.
Scooped by Jochen Schwenninger
Scoop.it!

Check out the demo that stole the show at Microsoft's all-hands meeting

Check out the demo that stole the show at Microsoft's all-hands meeting | Speech Recognition | Scoop.it
Wow, just, wow. Microsoft showed off an amalgam of technologies including gesture and natural language speech recognition, that translates sign language to text — in two languages. (Gesture and natural language speech recognition !
more...
No comment yet.
Scooped by Jochen Schwenninger
Scoop.it!

Tech Time Warp of the Week: IBM Speech Recognition, 1986 - Wired

Tech Time Warp of the Week: IBM Speech Recognition, 1986 - Wired | Speech Recognition | Scoop.it
Tech Time Warp of the Week: IBM Speech Recognition, 1986 Wired A pair of carefully painted lips, a feathered head-of-hair, pearl earrings, a pink button-down beneath a blue sweater, synthesizer music, a personal computer with a floppy drive, and a...
more...
No comment yet.
Scooped by Jochen Schwenninger
Scoop.it!

Microsoft Research shows a promising new breakthrough in speech translation technology - Next at Microsoft - Site Home - TechNet Blogs

Microsoft Research shows a promising new breakthrough in speech translation technology - Next at Microsoft - Site Home - TechNet Blogs | Speech Recognition | Scoop.it

...

Until recently though, even the best speech systems still had word error rates of 20-25% on arbitrary speech. Just over two years ago, researchers at Microsoft Research and the University of Toronto made another breakthrough. By using a technique called Deep Neural Networks, which is patterned after human brain behavior, researchers were able to train more discriminative and better speech recognizers than previous methods.

During my October 25 presentation in China, I had the opportunity to showcase the latest results of this work. We have been able to reduce the word error rate for speech by over 30% compared to previous methods. This means that rather than having one word in 4 or 5 incorrect, now the error rate is one word in 7 or 8. While still far from perfect, this is the most dramatic change in accuracy since the introduction of hidden Markov modeling in 1979, and as we add more data to the training we believe that we will get even better results...

 

more...
No comment yet.