Name
Title | ||
|---|---|---|
Feature Compensation Employing Multiple Environmental Models for Robust In-Vehicle Speech Recognition |
Abstract | ||
|---|---|---|
An effective feature compensation method is developed for reliable speech recognition in real-life in-vehicle environments. The CU-Move corpus, used for evaluation, contains a range of speech and noise signals collected for a number of speakers under actual driving conditions. PCGMM-based feature compensation, considered in this paper, utilizes parallel model combination to generate noise-corrupted speech model by combining clean speech and the noise model. In order to address unknown time-varying background noise, an interpolation method of multiple environmental models is employed. To alleviate computational expenses due to multiple models, an Environment Transition Model is employed, which is motivated from Noise Language Model used in Environmental Sniffing. An environment dependent scheme of mixture sharing technique is proposed and shown to be more effective in reducing the computational complexity. A smaller environmental model set is determined by the environment transition model for mixture sharing. The proposed scheme is evaluated on the connected single digits portion of the CU-Move database using the Aurora2 evaluation toolkit. Experimental results indicate that our feature compensation method is effective for improving speech recognition in real-life in-vehicle conditions. A reduction of 73.10% of the computational requirements was obtained by employing the environment dependent mixture sharing scheme with only a slight change in recognition performance. This demonstrates that the proposed method is effective in maintaining the distinctive characteristics among the different environmental models, even when selecting a large number of Gaussian components for mixture sharing. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1093/ietisy/e91-d.3.430 | IEICE Transactions |
Keywords | Field | DocType |
multiple environmental model,different environmental model,mixture sharing,environmental models,environment transition model,robust in-vehicle speech recognition,feature compensation employing multiple,reliable speech recognition,multiple model,smaller environmental model set,noise-corrupted speech model,noise model,clean speech,language model,speech recognition,computational complexity | Speech processing,Background noise,Pattern recognition,Computer science,Interpolation,Model selection,Speech recognition,Error detection and correction,Gaussian process,Artificial intelligence,Language model,Computational complexity theory | Journal |
Volume | Issue | ISSN |
E91-D | 3 | 1745-1361 |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wooil Kim | 1 | 120 | 16.95 |
| John H. L. Hansen | 2 | 3215 | 365.75 |