Name
Title | ||
|---|---|---|
Voice Activity Detection Based on Discriminative Weight Training Incorporating a Spectral Flatness Measure |
Abstract | ||
|---|---|---|
In this paper, we present an approach to incorporate discriminative weight training into a statistical model-based voice activity
detection (VAD) method. In our approach, the VAD decision rule is derived from the optimally weighted likelihood ratios (LRs)
using a minimum classification error (MCE) method. An adaptive on-line means of selecting two kinds of weights based on a
power spectral flatness measure (PSFM) is devised for performance improvement. The proposed approach is compared to conventional
schemes under various noise conditions, and shows better performance. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/s00034-009-9141-4 | CSSP |
Keywords | Field | DocType |
Voice activity detection, Minimum classification error, Statistical model, Power spectral flatness measure | Decision rule,Pattern recognition,Voice activity detection,Speech recognition,Spectral flatness,Artificial intelligence,Statistical model,Discriminative model,Strength training,Mathematics,Performance improvement | Journal |
Volume | Issue | ISSN |
29 | 2 | 1531-5878 |
Citations | PageRank | References |
2 | 0.49 | 12 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sang-Ick Kang | 1 | 25 | 4.81 |
| Joon-Hyuk Chang | 2 | 263 | 21.87 |