论文信息 - Energy Normalization in Automatic Speech Recognition

Energy Normalization in Automatic Speech Recognition

In this paper a novel method for energy normalization is presented. The objective of this method is to remove unwanted energy variations caused by different microphone gains, various loudness levels across speakers, as well as changes of single speaker loudness level over time. The solution presented here is based on principles used in automatic gain control. The use of this method results in relative improvement of the performances of an automatic speech recognition system by 26 %.

Dragisa Miskovic | Darko Pekar | Marko Janev | Niksa Jakovljevic

[1] E. Hänsler,et al. Acoustic Echo and Noise Control: A Practical Approach , 2004 .

[2] D. O'Shaughnessy,et al. Using noise reduction and spectral emphasis techniques to improve ASR performance in noisy conditions , 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

[3] Gerhard Schmidt,et al. Acoustic echo and noise control , 2004 .

[4] D. Pekar,et al. Vocal Tract Normalization Based on Formant Positions , 2006 .

[5] Douglas D. O'Shaughnessy,et al. Log-energy dynamic range normalization for robust speech recognition , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[6] Hanseok Ko,et al. Effective Energy Feature Compensation Using Modified Log-energy Dynamic Range Normalization for Robust Speech Recognition , 2007, IEICE Trans. Commun..

[7] D. O'Shaughnessy,et al. Incorporating frequency masking filtering in a standard MFCC feature extraction algorithm , 2004, Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004..

[8] Pietro Laface,et al. Impact of variabilities on speech recognition , 2006 .

[9] Sven Nordholm,et al. Evaluation and Modification of Cepstral Moment Normalization for Speech Recognition in Additive Babble Ensemble , 2006 .

[10] Marc Moonen,et al. Acoustic echo and noise control , 2005 .