Download as KEY, PPTX
More Related Content
Similar to Speech recognition
Speech recognition
- 1. Tiny Ears Using Speech Recognition To Teach Kids To Read Emily Toop Radical Robot Brighton iPhone Creators November 2011
- 2. What is SpeechRecognition? • Converting spoken words to text • Not targeted to a single speaker (voice recognition) • Utterances converted into phonemes that are compared against language model & grammar to generate a hypothesis • Recognition score to give confidence in hypothesis
- 3. Why is Speech The human brain is Recognition Hard? incredibly specialised - speech recognition & vision has taken millions of years to perfect. Hard to make a computer do the same thing. • Background Noise • Detecting gaps • Too many hypotheses generated • Accents • Other Languages • Dictionary words vs unknown words (i.e. names)
- 4. How Does SiriWork? • Protocol Cracked - https:// github.com/plamoni/SiriProxy • Server Based because of CPU & live data updates - doesn’t work offline • Limited vocabulary with well designed grammar
- 5. Device Based Recognition • Works offline • Immediate response for real time processing • No need for expensive data plans for your app to work
- 6. Device Based Recognition • Open Ears - http:// www.politepix.com/openears • Pocket Sphinx/ Sphinx CMU http:// cmusphinx.sourceforge.net/2010/03/ pocketsphinx-0-6-release/ • Limited Language Model • Limited Grammer
- 7.
- 8. Number Recogniser • ImportOpenEars .xcodeproj into project • Add OpenEars as target dependency • link libOpenEarsLibrary.a binary • Add OpenEars, SphinxBase & PocketSphinx to Header Search Path
- 9. Number Recogniser • Createand start audioSessionManager is delegate didFinishLaunchingWithOptions
- 10. Number recogniser • Rename.m file that runs PocketSphinxController to .mm • Add OpenEarsEventObserverDelegate
- 11.
- 12. Number recogniser • -(void)pocketsphinxRecognitionLoopDidStart{} • -(void)fliteDidFinishSpeaking{} (if using flite for text to speech)
- 13. Improving Recognition withFace Detection • Determine when user is speaking directly to app and not to another person to enhance accuracy • Stop listening when face not detected. • Detect when app has been abandoned & shut down audio manager etc. • Start listening when face is detected again
- 14. Demo • Decorator • UsingCore Image for face detection WWDC Session Videos numbers 419 & 422
- 15.
- 16.
- 17. Tiny Ears • iPadStorybook using Speech Recognition to listen to children as they read aloud • Detect when child stumbles or does not recognise a word & intervene with assistance to teach child to read word • Track reading progress over time to provide targeted feedback.
- 18. Problems - Educational • Large Age Range - different kids have different reading abilities and therefore require different levels of feedback/ intervention • Presenting learning in a fun way so nothing is so difficult child will give up rather than learn
- 19. Problems - Speech Recognition • 4 year olds speak very differently from adults • how do we detect errors? - unknown words & mispronounciations • ‘noise’ words, detecting coughs, laughs or sounds indicating distress or difficulty
- 20. Problems - Speech Recognition • Is the child present? • Is there more than one person present? • Whose speech should we process? • Can we even tell? • Can we detect if the child is in distress or struggling? • Can we detect reading ability through Speech Recognition?
- 21. Startup Chile • StartupAccelerator run by Chilean government • US$40k for 6 month, no equity • Starting January 16th • Looking for collborators from education, business, artificial intelligence - email me
- 22. Questions? • http://emilytoop.com • @fluffyemily •emily@radicalrobot.co.uk • http://radicalrobot.co.uk
Editor's Notes
- #2 \n
- #3 \n
- #4 Background Noise - solution possible Noise Rejection Microphones. These are getting better but still aren’t fantastic\nDetecting gaps - need loads of training data to train statistical model on expected speech patterns\nHypotheses - lots of CPU required to whittle them down to most likely\nAccents - More training data to cover accents and more CPU to match against language/grammar models\nOther Languages - need a new model or every language\n\n
- #5 \n
- #6 \n
- #7 \n
- #8 \n
- #9 \n
- #10 \n
- #11 \n
- #12 \n
- #13 \n
- #14 \n
- #15 \n
- #16 \n
- #17 \n
- #18 \n
- #19 \n
- #20 \n
- #21 error detection - car/care, ph vs f and silent letters - hour\n
- #22 1) should we ignore or accept sound input as speech?\n3) - visually or through ‘noise’ word detection\n\n
- #23 \n
- #24 \n