LinguisticFX 2.3 ::: Searching the Web by Voice ::: Easy-Share

by Jonathan Chambers, Shanghai.  Sidestep to LinguisticFX Parallelog to my personal blog.


Semantic Compositions [includes links to a variety of linguistics blogs]  

DEV: Gadgetry


1. China Alive & Visiting Authors 

2. Intellectual Property in China 

3. Alternative Web Tools 

4. Get Off My Weird Groove 

5. iSight Terror 

6. Collaborative Team Teaching 

7. Virtual Tour of Shanghai 


1. You're here

2. LinguisticFX 2.4 ::: Translation Hub


Read Page One of "Tales from the Language Center!"

Featured article: Searching the Web by Voice [PDF]

Alexander Franz (Google), Brian Milch (USC Berkeley)


Spoken queries are a natural medium for searching the Web in settings where typing on a keyboard is not practical. This paper describes a speech interface to the Google search engine. We present experiments with various statistical language models, concluding that a unigram model with collocations provides the best combination of broad coverage, predictive power, and real-time performance. We also report accuracy results of the prototype system.


This is a succinct (5 page) paper that describes the statistical linguistic model for calculating the viability of speech-activated search engine functionaility.  What fascinates me is that Google collates a search term corpus, from which collations and other linguistic relationships can be calculated as probabilities.   What this paper defines is a research procedure to determine a base lexis for digital speech processing to generate search queries.