Abstract | ||
---|---|---|
This paper describes the language modeling architectures and recognition experiments that enabled support of 'what-with-where' queries on GOOG-411. First we compare accuracy trade-offs between a single national business LM for business queries and using many small models adapted for particular cities. Experimental evaluations show that both approaches lead to comparable overall accuracy. Differences in the distributions of errors also lead to improvements from a simple combination. We then optimize variants of the national business LM in the context of combined business and location queries from the web, and finally evaluate these models on a recognition test from the recently fielded 'what-with-where' system. |
Year | Venue | Keywords |
---|---|---|
2009 | INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 | Language modeling, directory assistance, voice search, speech recognition |
Field | DocType | Citations |
Cache language model,Speech communication,Computer science,Modeling language,Speech recognition,Artificial intelligence,Natural language processing,Voice search,Language model,Directory assistance | Conference | 5 |
PageRank | References | Authors |
0.96 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Charl Johannes van Heerden | 1 | 133 | 12.50 |
Johan Schalkwyk | 2 | 461 | 40.80 |
Brian Strope | 3 | 95 | 10.99 |