Manner of pronunciation-influenced search results

摘要

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating search results. In one aspect, a method includes obtaining a transcription of a voice query, and data that identifies an accent of the voice query, submitting the transcription and the data that identifies the accent of the voice query to a search engine to generate one or more accent-influenced results of the voice query, and providing the accent-influenced results to a client device for display.

主权项

1. A system comprising:
one or more computers; and a computer-readable medium coupled to the one or more computers having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
obtaining a transcription of a voice query, and data that identifies a manner of pronunciation associated with a speaker of the voice query;submitting the transcription of the voice query and the data that identifies the manner of pronunciation associated with the speaker of the voice query to a search engine;receiving, from the search engine, one or more pronunciation-influenced search results of the voice query, wherein the one or more pronunciation-influenced search results of the voice query are search results that have been selected by the search engine based on both the transcription of the voice query and the manner of pronunciation associated with the speaker of the voice query;providing the pronunciation-influenced search results of the voice query to a client device for display;receiving a signal indicating that the speaker of the voice query that is associated with the manner of pronunciation has expressed interest in a particular pronunciation-influenced search result of the voice query; andadjusting a first score associated with the particular pronunciation-influenced search result of the voice query and the manner of pronunciation associated with the speaker of the voice query, based on receiving the signal, while not adjusting other scores associated with the particular pronunciation-influenced search result of the voice query and a different manner of pronunciation than the manner of pronunciation associated with the speaker of the voice query.