Abstract | ||
---|---|---|
In this letter, a novel approach is proposed to improve the performance of speech/music classification for the selectable mode vocoder (SMV) of 3GPP2 using the Gaussian mixture model (GMM). An in-depth analysis of the features and classification method adopted in the conventional SMV is performed. Feature vectors applied to the GMM are then selected from the relevant parameters of the SMV for efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme implemented in the SMV. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/LSP.2007.911184 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
speech classification,music classification,speech/music classification,vocoders,gaussian processes,selectable mode vocoder (smv),signal classification,feature vectors,audio signal processing,gaussian mixture model (gmm),selectable mode vocoder,gaussian mixture model,feature vector,linear predictive coding,adaptive filters,multiple signal classification,bandwidth | Feature vector,Pattern recognition,Selectable Mode Vocoder,Computer science,Speech recognition,Artificial intelligence,Signal classification,Gaussian process,Statistical classification,Audio signal processing,Mixture model,Encoding (memory) | Journal |
Volume | ISSN | Citations |
15 | 1070-9908 | 8 |
PageRank | References | Authors |
0.65 | 5 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jihyun Song | 1 | 15 | 4.36 |
Kye-hwan Lee | 2 | 19 | 2.92 |
Joon-Hyuk Chang | 3 | 83 | 6.64 |
Jong Kyu Kim | 4 | 46 | 9.40 |
Nam Soo Kim | 5 | 638 | 55.85 |