Broad phoneme class recognition in noisy environments using the GEMS
- Resource Type
- Conference
- Authors
- Demiroglu, C.; Anderson, D.V.
- Source
- Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004. Signals, Systems and Computers Signals, Systems and Computers, 2004. Conference Record of the Thirty-Eighth Asilomar Conference on. 2:1805-1808 Vol.2 2004
- Subject
- Signal Processing and Analysis
Computing and Processing
Working environment noise
Data mining
Feature extraction
Speech recognition
Speech processing
Speech enhancement
Sensor fusion
Sensor phenomena and characterization
Acoustic sensors
Fuses
- Language
Broad phoneme class recognition has the advantage of offering additional acoustic-phonetic knowledge to the speech processing applications. In several papers, exploiting such information is shown to be advantageous for HMM-based speech enhancement systems. The problem with those systems is the dramatic decrease in recognition accuracy in noisy environments. In this work, we extract the energy feature from an auxiliary sensor and directly fuse it with the features extracted from the speech signal. Experiment results with noisy speech show significant increase in performance.