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 412 Views

Recommend Documents

Natural Language Processing Research - Research at Google
Used numerous well known systems techniques. • MapReduce for scalability. • Multiple cores and threads per computer for efficiency. • GFS to store lots of data.

Efficient Natural Language Response ... - Research at Google
ceived email is run through the triggering model that decides whether suggestions should be given. Response selection searches the response set for good sug ...

Natural Language Processing (almost) from ... - Research at Google
Now available at http://trec.nist.gov/data/reuters/reuters.html. 17 .... this case A; for every pair of members Ai, Aj of that word class we ask how the sentence ...

K2Q: Generating Natural Language Questions ... - Research at Google
Nov 8, 2011 - Xiance Si. Google Inc. ... however, the keyword paradigm simply does not work. .... These operations do not take grammar into consid- eration ...

Statistical Parametric Speech Synthesis - Research at Google
Jun 9, 2014 - Text analysis. Model training x y x y λˆ. • Large data + automatic training. → Automatic voice building. • Parametric representation of speech.

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.

DIRECTLY MODELING SPEECH WAVEFORMS ... - Research at Google
statistical model [13], and mel-cepstral analysis-integrated hidden ..... Speech data in US English from a female professional speaker was used for the ...

Language and Speech
2 Hong Kong Institute of Education ... Conrad Perry, Swinburne University of Technology, School of Life and Social ...... of Phonetics, 26(2), 145–171. DELL, F.

Blunsom - Natural Language Processing Language Modelling and ...
Download. Connect more apps. ... Blunsom - Natural Language Processing Language Modelling and Machine Translation - DLSS 2017.pdf. Blunsom - Natural ...

LANGUAGE MODEL CAPITALIZATION ... - Research at Google
tions, the lack of capitalization of the user's input can add an extra cognitive load on the ... adding to their visual saliency. .... We will call this model the Capitalization LM. The ... rive that “iphone” is rendered as “iPhone” in the Ca

DISTRIBUTED DISCRIMINATIVE LANGUAGE ... - Research at Google
formance after reranking N-best lists of a standard Google voice-search data ..... hypotheses in domain adaptation and generalization,” in Proc. ICASSP, 2006.

EXPLORING LANGUAGE MODELING ... - Research at Google
ended up getting less city-specific data in their models. The city-specific system also includes a semantic stage for inverse text normalization. This stage maps the query variants like “comp usa” and ”comp u s a,” to the most common web- tex

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.

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.

DISCRIMINATIVE FEATURES FOR LANGUAGE ... - Research at Google
language recognition system. We train the ... lar approach to language recognition has been the MAP-SVM method [1] [2] ... turned into a linear classifier computing score dl(u) for utter- ance u in ... the error rate on a development set. The first .

Continuous Space Discriminative Language ... - Research at Google
confusion sets, and then discriminative training will learn to separate the ... quires in each iteration identifying the best hypothesisˆW ac- cording the current model. .... n-gram language modeling,” Computer Speech and Lan- guage, vol. 21, pp.

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-.

Fast and Scalable Decoding with Language ... - Research at Google
Jul 8, 2012 - a non-commercial open source licence†. .... all bilingual and parts of the provided monolingual data. newstest2008 is used for parameter.

Speech and Language Development.pdf
There was a problem previewing this document. Retrying... Download. Connect more apps... Try one of the apps below to open or edit this item. Speech and ...