Searching the Web by Voice

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.

• Type: Journal
• Year: 2002
• Where: COLING
• Authors: Alexander Franz, Brian Milch
• Keywords: COLING 2002, COLING 2008, Google Search Engine, Spoken Queries, Statistical Language Models