Speaker identification and localization using shuffled MFCC features and deep learning

International Journal of Speech Technology, vol. 26, pp. 185–196

Abstract

Abstract The use of machine learning in automatic speaker identification and localization systems has recently seen significant advances. However, this progress comes at the cost of using complex models, computations, and increasing the number of microphone arrays and training data. Therefore, in this work, we propose a new end-to-end identification and localization model based on a simple fully connected deep neural network (FC-DNN) and just two input microphones. This model can jointly or separately localize and identify an active speaker with high accuracy in single and multi-speaker scenarios by exploiting a new data augmentation approach. In this regard, we propose using a novel Mel Frequency Cepstral Coefficients (MFCC) based feature called Shuffled MFCC (SHMFCC) and its variant Difference Shuffled MFCC (DSHMFCC). In order to test our approach, we analyzed the performance of the identification and localization proposed model on the new features at different noise and reverberation conditions for single and multi-speaker scenarios. The results show that our approach achieves high accuracy in these scenarios, outperforms the baseline and conventional methods, and achieves robustness even with small-sized training data.

Authors 3

1. Mahdi Barhoush corresponding Aachen

   RWTH Aachen University

   Affiliation as printed

   INDA, RWTH Aachen, Aachen, Germany

2. Ahmed Hallawa Aachen Artificial Intelligence for Critical Care Lab

   Universitätsklinikum Aachen

   Affiliation as printed

   Artificial Intelligence for Critical Care Lab, University Hospital Aachen, Aachen, Germany

3. Anke Schmeink Aachen

   RWTH Aachen University

   Affiliation as printed

   INDA, RWTH Aachen, Aachen, Germany