Speaker Recognition Based on Deep Learning

Speaker recognition has made great progress under the laboratory environment, but in real life the performance of speaker recognition system is affected by various factors including environmental noise. This paper studies the performance of speaker recognition system in noisy environment and presents Speaker recognition system using modified Mel-Frequency Cepstral Coefficients (MFCC) technique based on different classifiers likes Euclidean distance, Back-Propagation Neural Network (BPNN), Self Organizing Map (SOM). Modified Mel-Frequency Cepstral Coefficients (MFCC) technique includes Blackman windowing instead of hamming window. This paper presents comparative plots of different classifiers based on modified Mel-Frequency Cepstral Coefficients (MFCC) technique. Speaker recognition system based on SOM Neural Network classifier provides better recognition rate compare to BPNN and Euclidean Distance based systems.

This paper investigates the influence of GSM speech coding on the performance of a text independent Speaker Recognition System (SRS). The SRS developed perform recognition on reconstructed speech waveform from the coded parameters using Gaussian Mixture Models (GMM) technique. The performance evaluation due to the use of the GSM speech coding namely the GSMEFR (Global System Mobile Enhanced Full Rate) codec was conducted, using three transcoded databases, obtained by passing the local ARADIGIT database through the GSM coder/decoder. The recognition evaluation was also conducted using original ARADIGIT sampled at 16 KHz and its 8 KHz downsampled version. The ARADIGIT database consists of 60 speakers (31 male speakers and 29 female speakers) pronouncing the ten Arabic digits five time each. Several experiments were conducted in order to evaluate the degradation introduced by different aspects of the simulated coder.

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Speaker recognition is an advanced method to identify a person from the biometric characteristics of speaking voice samples. Speaker recognition has become a vastly popular and useful research subject with countless essential applications in security, assistance, replication, authentication, automation, and verification. Many techniques are implemented using deep learning and neural network concepts and various datasets for speaker verification and identification. The primary goal of this work is to create improved robust techniques of speaker recognition to identify audio and enhance accuracy to human levels of comprehension. TIMIT and LibriSpeech datasets are used in this paper to develop an efficient automatic speaker recognition system. This work focuses on using MFCC to transform audio to spectrograms without losing the essential features of the audio file in question. We have used a closed set and an open set implementation procedure on these datasets. The closed set implementation uses a standard machine learning convention of utilizing the same datasets for training and testing, leading to higher accuracy. On the other hand, the open set implementation uses one dataset to train and another to test on each occasion. The accuracy, in this case, turned out to be relatively lower. On each dataset, CNN and LSTM deep learning techniques have been used to identify the sound, leading to the observation that implementing CNN resulted in a more significant accuracy.

In the field of information security, voice is one of the most important parts in biometrics. Especially, with the development of voice communication through the Internet or telephone system, huge voice data resources are accessed. In speaker recognition, voiceprint can be applied as the unique password for the user to prove his/her identity. However, speech with various emotions can cause an unacceptably high error rate and aggravate the performance of speaker recognition system. This paper deals with this problem by introducing a cost-sensitive learning technology to reweight the probability of test affective utterances in the pitch envelop level, which can enhance the robustness in emotion-dependent speaker recognition effectively. Based on that technology, a new architecture of recognition system as well as its components is proposed in this paper. The experiment conducted on the Mandarin Affective Speech Corpus shows that an improvement of 8% identification rate over the traditional speaker recognition is achieved.

This article presents a robust and efficient system for euro and Mexican banknote recognition. A high banknote recognition and classification rate was achieved using neural networks and deep learning with real scene images taken with both sunlight and artificial light. Without extracting characteristics by hand, the convolutional neural networks was fed with raw images. Analysis and experiments were carried out on banknotes based on key features, such as; watermarks, portraits on the bills, bill value written in words and numbers, and the complete banknotes. It was concluded that both the color information and some regions of the banknotes, as well as the banknote denomination written in words and numbers and the complete banknote, is the appropriate information to achieve a high rate of banknote classification and recognition. The experimental results show that the proposed approach is promising with quite remarkable results; it performs an efficient and robust classification using real scene images taken with both sunlight and artificial light and is invariant to banknote rotation and translation. A high recognition rate was achieved for Mexican banknotes and for euros. At present, the results contained herein are an improvement over thosereported in the state of the art.

Context. The questions of adapting the convolution neural network classifier use in automatic speaker recognition system of critical use(ASRSCU) are considered. The research object is the individual features of the human speech process.Objective. Development of means for separating individual features from the speaker’s speech signal, increasing their informativeness asa result of the factor analysis, their visual representation for the use of the convolution neural network classifier, and optimizing itsarchitecture for the needs of ASRSCU.Method. Measures are proposed to optimize the speaker recognition procedure of the ASRSCU, for which the optimal way of informativefeatures representation and the method of increasing their informativeness are theoretically justified, the topology and measures for increasingof the speaker recognition process efficiency are justified. In particular, it is justified the use of power normalized cepstral coefficients (PNCC)for the description of phonograms recorded in noisy environment conditions. We propose to use Gabor filters to represent information thatwill be analyzed by a convolution neural network, an optimal method of factor analysis (a sparse main components analyzing method) toreduce of the features vector length while preserving its informativeness, an improved topology of the convolution neural network in whichthe Gabor filters are integrated in to the convolution layer, which allows them to optimize their parameters during the neural network trainingprocess, and in a fully connected layer a deep neural network with a bottleneck layer is used, whose weights after training are uses as inputs forthe GMM/HMM control classifier.Results. Methods of representation and optimization of the speaker’s individual features, methods for their visual presentation andimprovement of the topology of a convolution neural network for making speaker recognition on their basis.Conclusions. The obtained theoretical results have found empirical confirmation. In particular, the stability of an improved convolutionneural network to the noisy input phonograms proved to be higher than the results of an ordinary convolution neural network and a deep neuralnetwork. With an SNR increase up to 10 dB, the GMM/HMM classifier is more efficient than the neural network, which can be explained by the efficiency of the used UBM models, but it is much more resource-intensive. Also, the parameters of the Gabor filter bank frames thatprovide the most variable individual features from the speech signal for speaker recognition are determined empirically.

Introduction. The significance of machine learning under the conditions of digital transformation of industry, and methods of implementing deep learning to provide the performance of trust management systems are considered. The necessity of using convolutional artificial neural networks for deep machine learning is determined. Various technologies and architectures for the implementation of artificial neural networks are briefly considered; a comparative analysis of their performance is carried out. The work objective is to study the need to develop new approaches to the architecture of computing machines for solving problems of deep machine learning in the trust management system implementation.Materials and Methods. In the context of digital transformation, the use of artificial intelligence reaches a new level. The technical implementation of artificial neural systems with deep machine learning is based on the use of one of three basic technologies: high performance computing (HPC) with parallel data processing, neuromorphic computing (NC), and quantum computing (QC).Results. Implementation models for deep machine learning, basic technologies and architecture of computing machines, as well as requirements for trust assurance in control systems using deep machine learning are analyzed. The problem of shortage of computation power for solving such problems is identified. None of the currently existing technologies can solve the full range of learning and impedance problems. The current level of technology does not provide information security and reliability of neural networks. The practical implementation of trust management systems with deep machine learning based on existing technologies for a significant part of the tasks does not provide a sufficient level of performance.Discussion and Conclusions. The study made it possible to identify the challenge of the computation power shortage for solving problems of deep machine learning. Through the analysis of the requirements for trust management systems, the external challenges of their implementation on the basis of existing technologies, and the need to develop new approaches to the computer architecture are determined.

Abstract— Audio data carries rich information in the form of speech, music, and environmental sounds, but its raw waveform is often complex and high-dimensional, making direct analysis difficult. Neural network architectures have emerged as powerful tools for extracting meaningful representations from audio signals, enabling efficient analysis and interpretation. Recurrent Neural Networks (RNNs), and Transformer-based models— for learning robust and discriminative features from audio. By automatically capturing temporal, spectral, and contextual patterns, these architectures significantly improve performance in tasks such as speech recognition, speaker identification, music classification, and environmental sound detection. The findings highlight the potential of neural networks to replace traditional handcrafted features, thereby advancing the development of scalable, accurate, and realtime audio processing applications. The rapid growth of audio data across domains such as speech, music, healthcare, and environmental monitoring has created a strong need for effective methods to extract meaningful representations from complex audio signals. Traditional approaches rely on handcrafted features like MFCCs and spectrogram descriptors, which often fail to capture the full temporal and spectral dynamics present in raw audio. Keywords: Neural Networks, Deep Learning, Audio Representation Learning, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformer Models, Feature Extraction, Speech Recognition, Speaker Identification, Sound Event Detection, Spectrogram Analysis, Audio Signal Processing

Identity recognition using the specific biometrical characteristics of a person has recently become a popular technique.Compared with image-sensor-data-based face and fingerprint recognition, speaker recognition using the acoustic characteristics of the uttered voices obtained from a speaking person is an additional alternative.In certain cases of dark environments or dirty fingers, acoustics-based speaker recognition will be an alternative method for accomplishing identity recognition with satisfactory recognition accuracy.Speaker recognition in practical application scenarios will inevitably encounter the problem of acoustic speech mixed with background noises.Utterances with undesired background noises of specific environments cannot be finely matched with the preestablished speaker models, thus causing inaccurate identity recognition results.To tackle this issue, we present a deep-learning-based method for speaker recognition in a noisy environment, which is a hybridization of two different types of deep learning calculation model, speech enhancement generative adversarial network (SEGAN) and convolutional neural network (CNN), called hybridized SEGAN-CNN.By removing specific background noise from the substandard utterance with noise using SEGAN and classifying the identities of numerous speaking subjects without noise effects using CNN, the task becomes speaker recognition in a clear environment, in which the robustness of speaker recognition can be effectively maintained.The results of experiments using a voice command phrase mixed with motor operation noise for robot navigation control in a simulated factory environment demonstrate the effectiveness of the proposed speaker recognition method.

Residual networks for text-independent speaker identification: Unleashing the power of residual learning

Objective. Neural decoding is an important tool in neural engineering and neural data analysis. Of various machine learning algorithms adopted for neural decoding, the recently introduced deep learning is promising to excel. Therefore, we sought to apply deep learning to decode movement trajectories from the activity of motor cortical neurons. Approach. In this paper, we assessed the performance of deep learning methods in three different decoding schemes, concurrent, time-delay, and spatiotemporal. In the concurrent decoding scheme where the input to the network is the neural activity coincidental to the movement, deep learning networks including artificial neural network (ANN) and long-short term memory (LSTM) were applied to decode movement and compared with traditional machine learning algorithms. Both ANN and LSTM were further evaluated in the time-delay decoding scheme in which temporal delays are allowed between neural signals and movements. Lastly, in the spatiotemporal decoding scheme, we trained convolutional neural network (CNN) to extract movement information from images representing the spatial arrangement of neurons, their activity, and connectomes (i.e. the relative strengths of connectivity between neurons) and combined CNN and ANN to develop a hybrid spatiotemporal network. To reveal the input features of the CNN in the hybrid network that deep learning discovered for movement decoding, we performed a sensitivity analysis and identified specific regions in the spatial domain. Main results. Deep learning networks (ANN and LSTM) outperformed traditional machine learning algorithms in the concurrent decoding scheme. The results of ANN and LSTM in the time-delay decoding scheme showed that including neural data from time points preceding movement enabled decoders to perform more robustly when the temporal relationship between the neural activity and movement dynamically changes over time. In the spatiotemporal decoding scheme, the hybrid spatiotemporal network containing the concurrent ANN decoder outperformed single-network concurrent decoders. Significance. Taken together, our study demonstrates that deep learning could become a robust and effective method for the neural decoding of behavior.

1 - Congruence of deep learning in biomedical engineering: future prospects and challenges

Deep learning, especially in the form of convolutional neural networks (CNNs), has triggered substantial improvements in computer vision and related fields in recent years. This progress is attributed to the shift from designing features and subsequent individual sub-systems towards learning features and recognition systems end to end from nearly unprocessed data. For speaker clustering, however, it is still common to use handcrafted processing chains such as MFCC features and GMM-based models. In this paper, we use simple spectrograms as input to a CNN and study the optimal design of those networks for speaker identification and clustering. Furthermore, we elaborate on the question how to transfer a network, trained for speaker identification, to speaker clustering. We demonstrate our approach on the well known TIMIT dataset, achieving results comparable with the state of the art-without the need for handcrafted features.

In recent years, Adaptive Optics (AO) system is developing towards miniaturization and low cost. Because of its simple structure and wide application range, wavefront sensorless (WFSless) AO system has become a research hotspot in related fields. Under the condition that the hardware environment is determined, the system control algorithm determines the correction effect and convergence speed of WFSless AO system. The emerging deep learning and artificial neural network have injected new vitality into the control algorithms of WFSless AO system, and further promoted the theoretical and practical development of WFSless AO. On the basis of summarizing the previous control algorithms of WFSless AO system, the applications of convolution neural network (CNN), long-term memory neural network (LSTM) and deep reinforcement learning in WFSless AO system control in recent years are comprehensively introduced, and characteristics of various deep learning models in WFSless AO system are summarized. Applications of WFSless AO system in astronomical observation, microscopy, ophthalmoscopy, laser telecommunication and other fields are outlined.