This article verifies the reliability of automatic speaker verification (ASV) systems on new synthesis methods based on deep neural networks. ASV systems are widely used and applied regarding secure and effective biometric authentication. On the other hand, the rapid deployment of ASV systems contributes to the increased attention of attackers with newer and more sophisticated spoofing methods. Until recently, speech synthesis of the reference speaker did not seriously compromise the latest ASV systems. This situation is changing with the deployment of deep neural networks into the synthesis process. Projects including WaveNet, Deep Voice, Voice Loop, and many others generate very natural and high-quality speech that may clone voice identity. We are slowly approaching an era where we will not be able to recognize a genuine voice from a synthesized one. Therefore, it is necessary to define the robustness of current ASV systems to new methods of voice cloning. In this article, well-known SVM and GMM as well as new CNN-based ASVs are applied and subjected to synthesized speech from Tacotron 2 with the WaveNet TTS system. The results of this work confirm our concerns regarding the reliability of ASV systems against synthesized speech.
The impact of the classification method and features selection for the speech emotion recognition accuracy is discussed in this paper. Selecting the correct parameters in combination with the classifier is an important part of reducing the complexity of system computing. This step is necessary especially for systems that will be deployed in real‐time applications. The reason for the development and improvement of speech emotion recognition systems is wide usability in nowadays automatic voice controlled systems. Berlin database of emotional recordings was used in this experiment. Classification accuracy of artificial neural networks, k‐nearest neighbours, and Gaussian mixture model is measured considering the selection of prosodic, spectral, and voice quality features. The purpose was to find an optimal combination of methods and group of features for stress detection in human speech. The research contribution lies in the design of the speech emotion recognition system due to its accuracy and efficiency.
Besides facial expression or gestures, human speech is still the main channel of communication in ordinary human life. In addition to speech content, this signal also contains additional source / human status information. Gender, age, but also the emotional state of man can be extracted from spoken speech. This research is focused on the classification of the emotional state of man, the stress in particular. Accordingly, we have created a speech database of emergency phone calls. The database contains recordings of the Integrated Rescue System (IRS) of 112 emergency line from Czech Republic. It was designed to detect the stress from the human voice. Due to the detection of stress from a neutral (resting) state, the database was divided into neutral speech and human speech in stress. The neutral subgroup consists of voice recordings of the IRS operator. The stress subgroup is made up of people in danger. We have deliberately selected events with great stressful stimuli such as car accident, domestic violence, situations close to death, and so on. The speech signal is then pre-processed and analyzed for the feature extraction. The feature vectors represents classifier input data. Old-fashioned classification methods such as Support Vector Machine (SVM) or k-Nearest Neighbors (k-NN) classifiers and new artificial intelligence methods such as Convolutional Neural Networks (CNN) are used to detect and recognize human stress. The applications of achieved results are broad: from phone services through Smart Health to security components analysis.