System and method for speech-enabled access to media content by a ranked normalized weighted graph using speech recognition
View Patent ↗Disclosed herein are systems, methods, and computer-readable storage media for generating a speech recognition model for a media content retrieval system. The method causes a computing device to retrieve information describing media available in a media content retrieval system, construct a graph that models how the media are interconnected based on the retrieved information, rank the information describing the media based on the graph, and generate a speech recognition model based on the ranked information. The information can be a list of actors, directors, composers, titles, and/or locations. The graph that models how the media are interconnected can further model pieces of common information between two or more media. The method can further cause the computing device to weight the graph based on the retrieved information, wherein the weighted graph is further normalized to yield a normalized weighted graph to help with speech query searching of media content using speech recognition. The graph can further model relative popularity information in the list. The method can rank information based on a PageRank algorithm.
1. A method comprising:
constructing, via a processor device, a media interconnection graph which models how media are interconnected by connecting disparate categories of the media;
weighting the media interconnection graph based on a popularity of the media, to yield a weighted graph;
normalizing the weighted graph, to yield a normalized weighted graph;
generating, via the processor device, a speech recognition model based on the normalized weighted graph;
receiving audible speech for searching media content; and
converting the audible speech to output a graph using the speech recognition model.
2. The method of claim 1 , wherein the media interconnection graph links information comprising actors, directors, composers, titles, and locations.
3. The method of claim 2 , wherein the constructing of the media interconnection graph is further based on common information in two media.
4. The method of claim 2 , further comprising adjusting, prior to the normalizing, the weighted graph based on the common information.
5. The method of claim 2 , wherein the media interconnection graph further models relative popularity of each piece of the common information.
6. The method of claim 1 , further comprising ranking information used to build the media interconnection graph, wherein the ranking is performed using a web-page ranking algorithm.
7. The method of claim 6 , further comprising running the web-page ranking algorithm until convergence.
8. The method of claim 1 , further comprising updating the speech recognition model based on additional retrieved information.
9. The method of claim 1 , wherein the media interconnection graph models relative respective popularity of each piece of the media.
10. The method of claim 1 , wherein the speech recognition model is a hierarchical language model.
11. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
constructing a media interconnection graph which models how media are interconnected by connecting disparate categories of the media;
weighting the media interconnection graph based on a popularity of the media, to yield a weighted graph;
normalizing the weighted graph, to yield a normalized weighted graph;
generating a speech recognition model based on the normalized weighted graph;
receiving audible speech for searching media content; and
converting the audible speech to output a graph using the speech recognition model.
12. The system of claim 11 , wherein the media interconnection graph links information comprising actors, directors, composers, titles, and locations.
13. The system of claim 12 , wherein the constructing of the media interconnection graph is further based on common information in two media.
14. The system of claim 12 , further comprising adjusting, prior to the normalizing, the weighted graph based on the common information.
15. The system of claim 12 , wherein the media interconnection graph further models relative popularity of each piece of the common information.
16. The system of claim 11 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in the processor performing operations comprising ranking information used to build the media interconnection graph, wherein the ranking is performed using a web-page ranking algorithm.
17. The system of claim 16 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in the processor performing operations comprising running the web-page ranking algorithm until convergence.
18. The system of claim 11 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in the processor performing operations comprising updating the speech recognition model based on additional retrieved information.
19. The system of claim 11 , wherein the media interconnection graph models relative respective popularity of each piece of the media.
20. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
constructing a media interconnection graph which models how media are interconnected by connecting disparate categories of the media;
weighting the media interconnection graph based on a popularity of the media, to yield a weighted graph;
normalizing the weighted graph, to yield a normalized weighted graph;
generating a speech recognition model based on the normalized weighted graph;
receiving audible speech for searching media content; and
converting the audible speech to output a graph using the speech recognition model.