Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Modulation spectrum exponential weighting for robust speech recognition
In this paper, we present a novel scheme to improve the noise robustness of features in speech recognition for vehicle noise environments. In the algorithm termed modulation spectrum exponential weighting (MSEW), the magnitude spectra of feature streams are updated by integrating a reference magnitude spectrum and the original magnitude spectrum with varying exponential weights based on the signal-to-noise ratio (SNR) of the operating environment. Specifically, we present three modes of MSEW, which can be viewed as a generalization of the two algorithms, modulation spectrum replacement/filtering (MSR/MSF). In experiments conducted on the AURORA-2 noisy digit database, the presented MSEW algorithms can achieve better recognition accuracy rates relative to the original MSR and MSF in various vehicle-noise environments.
Modulation spectrum exponential weighting for robust speech recognition
In this paper, we present a novel scheme to improve the noise robustness of features in speech recognition for vehicle noise environments. In the algorithm termed modulation spectrum exponential weighting (MSEW), the magnitude spectra of feature streams are updated by integrating a reference magnitude spectrum and the original magnitude spectrum with varying exponential weights based on the signal-to-noise ratio (SNR) of the operating environment. Specifically, we present three modes of MSEW, which can be viewed as a generalization of the two algorithms, modulation spectrum replacement/filtering (MSR/MSF). In experiments conducted on the AURORA-2 noisy digit database, the presented MSEW algorithms can achieve better recognition accuracy rates relative to the original MSR and MSF in various vehicle-noise environments.
Modulation spectrum exponential weighting for robust speech recognition
Hao-teng Fan, (Autor:in) / Yi-cheng Lian, (Autor:in) / Jeih-weih Hung, (Autor:in)
01.11.2012
340459 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Robust Geodetic Parameter Estimation throuyh Iterative Weighting
| Online Contents | 1994
Approaches to Robust Speech Recognition in Mobile Devices
| British Library Conference Proceedings | 2005
Construction of Anytime Algorithms for Robust Speech Recognition
| British Library Conference Proceedings | 2015
Weighting Landscapes, Weighting People
| British Library Online Contents | 1992
Robust Acoustic Speech Emotion Recognition by Ensembles of Classifiers
| British Library Conference Proceedings | 2005