Searching by Talking:Analysis of Voice Queries on Mobile Web Search

摘要

The growing popularity of mobile search and the advance-ment in voice recognition technologies have opened the doorfor web search users to speak their queries, rather than typethem. While this kind of voice search is still in its infancy,it is gradually becoming more widespread. In this paper,we examine the logs of a commercial search engine's mobileinterface, and compare the spoken queries to the typed-inqueries. We place special emphasis on the semantic andsyntactic characteristics of the two types of queries. Wealso conduct an empirical evaluation showing that the lan-guage of voice queries is closer to natural language thantyped queries. Our analysis reveals further dierences be-tween voice and text search, which have implications for thedesign of future voice-enabled search tools.