Weighted training for speech under Lombard Effect for speaker recognition

Muhammad Muneeb Saleem, Gang Liu, John H.L. Hansen
2015 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
The presence of Lombard Effect in speech is proven to have severe effects on the performance of speech systems, especially speaker recognition. Varying kinds of Lombard speech are produced by speakers under influence of varying noise types [1] . This study proposes a high-accuracy classifier using deep neural networks for detecting various kinds of Lombard speech against neutral speech, independent of the noise levels causing the Lombard Effect. Lombard Effect detection accuracies as high as
more » ... acies as high as 95.7% are achieved using this novel model. The deep neural network based classification is further exploited by validation based weighted training of robust i-Vector based speaker identification systems. The proposed weighted training achieves a relative EER improvement of 28.4% over an i-Vector baseline system, confirming the effectiveness of deep neural networks in modeling Lombard Effect. Index Terms-Lombard Effect, deep neural networks, speaker identification, robust, weighted training 978-1-4673-6997-8/15/$31.00
doi:10.1109/icassp.2015.7178792 dblp:conf/icassp/SaleemLH15 fatcat:rrlosolt7fhvthzrcwhbcmbrfq