Title | ||
---|---|---|
Four-layer categorization scheme of fast GMM computation techniques in large vocabulary continuous speech recognition systems |
Abstract | ||
---|---|---|
Large vocabulary continuous speech recognition systems are known to be computationally intensive. A major bottle- neck is the Gaussian mixture model (GMM) computation and various techniques have been proposed to address this problem. We present a systematic study of fast GMM computation tech- niques. As there are a large number of these and it is imprac- tical to exhaustively evaluate all of them, we first categorized techniques into four layers and selected representative ones to evaluate in each layer. Based on this framework of study, we provide a detailed analysis and comparison of GMM computa- tion techniques from the four-layer perspective and explore two subtle practical issues, 1) how different techniques can be com- bined effectively and 2) how beam pruning will affect the per- formance of GMM computation techniques. All techniques are evaluated in the CMU Communicator domain. We also com- pare their performance with others reported in the literature. |
Year | Venue | Keywords |
---|---|---|
2004 | INTERSPEECH | gaussian mixture model |
Field | DocType | Citations |
Categorization,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Natural language processing,Vocabulary,Computation | Conference | 27 |
PageRank | References | Authors |
2.51 | 7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arthur Chan | 1 | 239 | 15.28 |
Mosur Ravishankar | 2 | 250 | 19.46 |
Alex Rudnicky | 3 | 1726 | 202.34 |
Jahanzeb Sherwani | 4 | 181 | 16.59 |