Recommending language models for search queries based on user profile

A method for generating results in multiple languages for search queries, comprising:

• receiving, via an audio input device, a first voice query from a user, wherein the user corresponds to a user profile that is stored in memory, and wherein the user profile indicates a first language model for a first language and a second language model for a second language for determining search results;
• identifying, using control circuitry, a first audio segment and a second audio segment based on audible breaks in the first voice query;
• using the control circuitry, determining, for a first text query, a first resolved word in a first language and a second resolved word in the first language by combining a first set of phonemes to the first audio segment and second audio segment, respectively, wherein the first set of phonemes are selected from phonemes of the first language model;
• using the control circuitry, determining a first numerical ranking for the first resolved word in the first language and a second numerical ranking for the second resolved word in the first language based on a likelihood of usage of the first resolved word in the first language and the second resolved word in the first language;
• using the control circuitry, determining a first composite score for the first text query based on summing the first numerical ranking and the second numerical ranking;
• using the control circuitry, determining, for a second text query, a first resolved word in a second language and a second resolved word in the second language by combining a second set of phonemes to the first audio segment and second audio segment, respectively, wherein the second set of phonemes are selected from phonemes of the second language model;
• using the control circuitry, determining a third numerical ranking for the first resolved word in the second language and a fourth numerical ranking for the second resolved word in the second language based on a likelihood of usage of the first resolved word in the second language and the second resolved word in the second language;
• using the control circuitry, determining a second composite score for a second text query based on summing the third numerical ranking and the fourth numerical ranking;
• and
• using the control circuitry, generating for display, on the display device, a first search result for the first text query and a second search result for the second text query, wherein the first search result and the second search result are ordered according to the first composite ranking and the second composite ranking, respectively.

A system for generating results in multiple languages for search queries, comprising:

• memory configured to store a plurality of language models;
• and
• control circuitry configured to:
• receive, via an audio input device, a first voice query from a user, wherein the user corresponds to a user profile that is stored in memory, and wherein the user profile indicates a first language model for a first language and a second language model for a second language for determining search results;
• identify a first audio segment and a second audio segment based on audible breaks in the first voice query;
• determine, for a first text query, a first resolved word in a first language and a second resolved word in the first language by combining a first set of phonemes to the first audio segment and second audio segment, respectively, wherein the first set of phonemes are selected from phonemes of the first language model;
• determine a first numerical ranking for the first resolved word in the first language and a second numerical ranking for the second resolved word in the first language based on a likelihood of usage of the first resolved word in the first language and the second resolved word in the first language;
• determine a first composite score for the first text query based on summing the first numerical ranking and the second numerical ranking;
• determine, for a second text query, a first resolved word in a second language and a second resolved word in the second language by combining a second set of phonemes to the first audio segment and second audio segment, respectively, wherein the second set of phonemes are selected from phonemes of the second language model;
• determine a third numerical ranking for the first resolved word in the second language and a fourth numerical ranking for the second resolved word in the second language based on a likelihood of usage of the first resolved word in the second language and the second resolved word in the second language;
• determine a second composite score for a second text query based on summing the third numerical ranking and the fourth numerical ranking;
• and
• generate for display, on the display device, a first search result for the first text query and a second search result for the second text query, wherein the first search result and the second search result are ordered according to the first composite ranking and the second composite ranking, respectively.