Speech and Natural Language Where are we now, and where are we heading? Ciprian Chelba [email protected]

04/16/2013 Ciprian Chelba, Quo Vadis Speech and Natural Language – p. 1

Case Study:Google Search by Voice

What contributed to success: clearly set user expectation by existing text app (proverbial “killer-app”) excellent language model built from query stream great progress in acoustic modeling using neural networks clean speech: users are motivated to articulate clearly smartphones do high quality speech capture speech transferred to server error-free over IP iterations over log (both text and speech) data from users

04/16/2013 Ciprian Chelba, Quo Vadis Speech and Natural Language – p. 2

Challenges and Directions: Speech Recognition

Automatic speech recognition is incredibly complex. Problem is fundamentally unsolved. data availability and computing have changed significantly since the mid-90s 2-3 orders of magnitude more data and computing are available re-visit (simplify!) modeling choices made on corpora of modest size multi-linguality built-in from start, not as an after-thought managing complexity while delivering the best performance across many languages, applications, etc. 04/16/2013 Ciprian Chelba, Quo Vadis Speech and Natural Language – p. 3

Challenges and Directions: Natural Language Understanding and Dialog

Very hard problem that has been underestimated and somewhat neglected. develop with the users in the loop to get data, and set/understand user expectation data-driven natural language engineering, not hacks multi-sensory setup: leverage touch screen, geo-location, perhaps accelerometer multi-linguality built-in from start, not as an after-thought managing complexity while delivering the best performance across many languages, applications, etc. 04/16/2013 Ciprian Chelba, Quo Vadis Speech and Natural Language – p. 4

Speech and Natural Language: Quo Vadis?

Would the technology be the same if we were to restart ASR/NLU research on today’s data availability and computing platform?

04/16/2013 Ciprian Chelba, Quo Vadis Speech and Natural Language – p. 5

Speech and Natural Language - Research at Google

Apr 16, 2013 - clearly set user expectation by existing text app. (proverbial ... develop with the users in the loop to get data, and set/understand user ...

43KB Sizes 4 Downloads 216 Views

Recommend Documents

Large Vocabulary Automatic Speech ... - Research at Google
Sep 6, 2015 - child speech relatively better than adult. ... Speech recognition for adults has improved significantly over ..... caying learning rate was used. 4.1.

AUTOMATIC LANGUAGE IDENTIFICATION IN ... - Research at Google
this case, analysing the contents of the audio or video can be useful for better categorization. ... large-scale data set with 25000 music videos and 25 languages.

Action Language Hybrid AL - Research at Google
the idea of using a mathematical model of the agent's domain, created using a description in the action language AL [2] to find explanations for unexpected.

Language-independent Compound Splitting ... - Research at Google
trained using a support vector machine classifier. Al- fonseca et al. ..... 213M 42,365. 44,559 70,666 .... In A. Gelbukh, editor, Lecture Notes in Computer Sci-.