The performance of speaker recognition systems is very well on the datasets without noise and mismatch. However, the performance gets degraded with the environmental noises, channel variation, physical and behavioral changes in speaker. The types of Speaker related feature play crucial role in improving the performance of speaker recognition systems. Gammatone Frequency Cepstral Coefficient (GFCC) features has been widely used to develop robust speaker recognition systems with the conventional machine learning, it achieved better performance compared to Mel Frequency Cepstral Coefficient (MFCC) features in the noisy condition. Recently, deep learning models showed better performance in the speaker recognition compared to conventional machine learning. Most of the previous deep learning-based speaker recognition models has used Mel Spectrogram and similar inputs rather than a handcrafted features like MFCC and GFCC features. However, the performance of the Mel Spectrogram features gets degraded in the high noise ratio and mismatch in the utterances. Similar to Mel Spectrogram, Cochleogram is another important feature for deep learning speaker recognition models. Like GFCC features, Cochleogram represents utterances in Equal Rectangular Band (ERB) scale which is important in noisy condition. However, none of the studies have conducted analysis for noise robustness of Cochleogram and Mel Spectrogram in speaker recognition. In addition, only limited studies have used Cochleogram to develop speech-based models in noisy and mismatch condition using deep learning. In this study, analysis of noise robustness of Cochleogram and Mel Spectrogram features in speaker recognition using deep learning model is conducted at the Signal to Noise Ratio (SNR) level from −5 dB to 20 dB. Experiments are conducted on the VoxCeleb1 and Noise added VoxCeleb1 dataset by using basic 2DCNN, ResNet-50, VGG-16, ECAPA-TDNN and TitaNet Models architectures. The Speaker identification and verification performance of both Cochleogram and Mel Spectrogram is evaluated. The results show that Cochleogram have better performance than Mel Spectrogram in both speaker identification and verification at the noisy and mismatch condition.

The performance of speaker recognition is very well in a clean dataset or without mismatch between training and test set. However, the performance is degraded with noise, channel variation, physical and behavioral changes with the speaker. The studies confirmed that the features which represent speech in the Equal Rectangular Band (ERB) scale are more robust than Mel Scale at low Signal to Noise Ratio (SNR) level. Gammatone Frequency Cepstral Coefficient (GFCC) which represents speech in ERB scale is widely used in classical machine learning based speaker recognition at noisy conditions. Recently, deep learning models are widely applied in speaker recognition and show better performance than classical machine learning. Previous deep learning based speaker recognition models used Mel Spectrogram as an input rather than hand crafted features. However, the performance of Mel spectrogram drastically degraded at low SNR level because Mel Spectrogram represents speech in Mel Scale. Cochleogram is another important input to develop deep learning based speaker recognition models. Cochleogram represents speech in ERB scale, which is more robust at low SNR level. However, none of the studies used the Cochleogram feature to develop deep learning based speaker recognition models. In addition, none of the studies conduct analysis of noise robustness of Cochleogram and Mel Spectrogram features in speaker recognition using deep learning. In this study, we conducted an analysis of noise robustness of Cochleogram and Mel Spectrogram features in speaker recognition by using additive noises (such as: babble, street and restaurant noises).The train-clean-100 part of the LibriSpeech dataset, which consists of 251 speakers (126 male and 125 female speakers) and 28,539 utterances is used for the experiment. CNN model is used for training and classification of speakers into different classes. The evaluation results show that Cochleogram is more robust than Mel Spectrogram at low SNR level. Both Cochleogram and Mel Spectrogram features show approximately equal accuracy at high SNR and without additive noise. In conclusion, the Cochleogram feature improves performance of deep learning based speaker recognition in noisy conditions.

Speaker recognition has crucial application in forensic science, financial areas, access control, surveillance and law enforcement. The performance of speaker recognition get degraded with the noise, speakers physical and behavioral changes. Fusion of Mel Frequency Cepstral Coefficient (MFCC) and Gammatone Frequency Cepstral Coefficient (GFCC) features are used to improve the performance of machine learning based speaker recognition systems in the noisy condition. Deep learning models, especially Convolutional Neural Network (CNN) and its hybrid approaches outperform machine learning approaches in speaker recognition. Previous CNN based speaker recognition models has used Mel Spectrogram features as an input. Even though, Mel Spectrogram features show better performance compared to the handcrafted features, its performance get degraded with noise and behavioral changes of speaker. In this work, a CNN based speaker recognition model is developed using fusion of Mel Spectrogram and Cochleogram feature as input. The speaker recognition performance of the fusion of Mel Spectrogram and Cochleogram features is compared with the performance of Mel Spectrogram and Cochleogram features without fusing. The train-clean-100 part of the LibriSpeech dataset, which consists of 251 speakers (126 male and 125 female speakers) and 28,539 utterances is used for the experiment of proposed model. CNN model is trained and evaluated for 20 epochs using training and validation data respectively. Proposed speaker recognition model which uses fusion of Mel Spectrogram and Cochleogram as input for CNN has accuracy of 99.56%. Accuracy of CNN based speaker recognition with Mel Spectrogram is 98.15% and Cochleogram features is 97.43%. The results show that fusion of Mel Spectrogram and Cochleogram features improve the performance of speaker recognition.

Speaker identification is biometrics that classifies or identifies a person from other speakers based on speech characteristics. Recently, deep learning models outperformed conventional machine learning models in speaker identification. Spectrograms of the speech have been used as input in deep learning-based speaker identification using clean speech. However, the performance of speaker identification systems gets degraded under noisy conditions. Cochleograms have shown better results than spectrograms in deep learning-based speaker recognition under noisy and mismatched conditions. Moreover, hybrid convolutional neural network (CNN) and recurrent neural network (RNN) variants have shown better performance than CNN or RNN variants in recent studies. However, there is no attempt conducted to use a hybrid CNN and enhanced RNN variants in speaker identification using cochleogram input to enhance the performance under noisy and mismatched conditions. In this study, a speaker identification using hybrid CNN and the gated recurrent unit (GRU) is proposed for noisy conditions using cochleogram input. VoxCeleb1 audio dataset with real-world noises, white Gaussian noises (WGN) and without additive noises were employed for experiments. The experiment results and the comparison with existing works show that the proposed model performs better than other models in this study and existing works.