Recommending language models for search queries based on user profile

1. 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, generating a first text query, the first text query including a first resolved word in a first language and a second resolved word in the first language determined 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.

2. The method of claim 1 , wherein the user profile is automatically updated to add a third language model for a third language for determining search results, without user input, in response to determining that metadata for a third search result indicates that the third search result corresponds to the third language.

3. The method of claim 2 , wherein the user profile is updated after receiving a user confirmation to apply the third language model for determining search results, wherein a prompt for receiving the user confirmation is generated for display in response to determining that the metadata for the third search result indicates that the third search result corresponds to the third language.

4. The method of claim 3 , wherein updating the user profile further comprises:

retrieving a language setting from the user profile;

comparing a language corresponding to the language setting to the third language; and

determining that the third language does not correspond to the language corresponding to the language setting.

5. The method of claim 4 , further comprising:

receiving, via the audio input device, a second voice query from the user;

identifying a third audio segment and a fourth audio segment based on audible breaks in the second voice query; and

determining, for a third text query, a first resolved word in the third language and a second resolved word in the third language by combining a third set of phonemes to the third audio segment and fourth audio segment, respectively, wherein the third set of phonemes are selected from phonemes of the third language model.

6. The method of claim 1 , further comprising:

determining multiple potential text queries using the first language model by applying different combinations of the first set of phonemes to the first audio segment and second audio segment, respectively;

ranking the potential text queries according to their respective composite scores; and

identifying the first text query from the potential text queries based on the first composite score having a highest rank of the respective composite scores.

7. The method of claim 6 , further comprising prompting the user to select the first text query if multiple text queries of the potential text queries share the highest rank of the respective composite scores.

8. The method of claim 7 , further comprising:

determining to generate for display the first search result for the first text query in response to determining that the first composite score is above a threshold score.

9. The method of claim 8 , further comprising:

retrieving, from the memory, first metadata for the first search result;

automatically determining that the first metadata for the first search result indicates that the first search result does not correspond to the first language; and

not generating for display the first search result for the first text query in response to determining that the first metadata for the first search result indicates that the first search result does not correspond to a first language.

10. The method of claim 1 , further comprising:

determining, for a third text query, the first resolved word in the first language and the second resolved word in the second language by combining the first set of phonemes to the first audio segment and the second set of phonemes to the second audio segment;

determining a fifth numerical ranking for the first resolved word in the first language and a sixth numerical ranking for the second resolved word in the second language based on a likelihood of usage of the first resolved word in the first language and the second resolved word in the second language; and

determining a third composite score for the third text query based on summing the fifth numerical ranking and the sixth numerical ranking.

11. 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;

generate a first text query, the first text query including a first resolved word in a first language and a second resolved word in the first language determined 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.

12. The system of claim 11 , wherein the user profile is automatically updated to add a third language model for a third language for determining search results, without user input, in response to determining that metadata for a third search result indicates that the third search result corresponds to the third language.

13. The system of claim 12 , wherein the user profile is updated after receiving a user confirmation to apply the third language model for determining search results, wherein a prompt for receiving the user confirmation is generated for display in response to determining that the metadata for the third search result indicates that the third search result corresponds to the third language.

14. The system of claim 13 , wherein updating the user profile further comprises:

retrieving a language setting from the user profile;

comparing a language corresponding to the language setting to the third language; and

determining that the third language does not correspond to the language corresponding to the language setting.

15. The system of claim 14 , wherein the control circuitry is further configured to:

receive, via the audio input device, a second voice query from the user;

identify a third audio segment and a fourth audio segment based on audible breaks in the second voice query; and

determine, for a third text query, a first resolved word in the third language and a second resolved word in the third language by combining a third set of phonemes to the third audio segment and fourth audio segment, respectively, wherein the third set of phonemes are selected from phonemes of the third language model.

16. The system of claim 11 , wherein the control circuitry is further configured to:

determine multiple potential text queries using the first language model by applying different combinations of the first set of phonemes to the first audio segment and second audio segment, respectively; and

rank the potential text queries according to their respective composite scores; and

identify the first text query from the potential text queries based on the first composite score having a highest rank of the respective composite scores.

17. The system of claim 16 , wherein the control circuitry is further configured to prompt the user to select the first text query if multiple text queries of the potential text queries share the highest rank of the respective composite scores.

18. The system of claim 17 , wherein the control circuitry is further configured to determine to generate for display the first search result for the first text query in response to determining that the first composite score is above a threshold score.

19. The system of claim 18 , wherein the control circuitry is further configured to:

retrieve, from the memory, first metadata for the first search result;

automatically determine that the first metadata for the first search result indicates that the first search result does not correspond to the first language; and

not generate for display the first search result for the first text query in response to determining that the first metadata for the first search result indicates that the first search result does not correspond to a first language.

20. The system of claim 11 , wherein the control circuitry is further configured to:

determine, for a third text query, the first resolved word in the first language and the second resolved word in the second language by combining the first set of phonemes to the first audio segment and the second set of phonemes to the second audio segment;

determine a fifth numerical ranking for the first resolved word in the first language and a sixth numerical ranking for the second resolved word in the second language based on a likelihood of usage of the first resolved word in the first language and the second resolved word in the second language; and

determine a third composite score for the third text query based on summing the fifth numerical ranking and the sixth numerical ranking.