A Primer on Deep Learning Architectures and Applications in Speech Processing

Ogunfunmi, Tokunbo; Ramachandran, Ravi P.; Togneri, Roberto; Zhao, Yuanjun; Xia, Xianjun

doi:10.1007/s00034-019-01157-3

Cited by 20 publications

(11 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recurrent neural networks (RNNs) are a group of DL models employed in speech recognition (Ogunfunmi et al, 2019 ), natural language processing (Deng and Liu, 2018 ), and biomedical signal processing (Vicnesh et al, 2020 ; Baygin et al, 2021 ). CNN models are of Feed-Forward types.…”

Section: Methodsmentioning

confidence: 99%

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Shoeibi

Sadeghi

Moridian

et al. 2021

Front. Neuroinform.

107

View full text Add to dashboard Cite

Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames and then were normalized by z-score or norm L2. In the classification step, two different approaches were considered for SZ diagnosis via EEG signals. In this step, the classification of EEG signals was first carried out by conventional machine learning methods, e.g., support vector machine, k-nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, and bagging. Various proposed DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), and 1D-CNN-LSTMs, were used in the following. In this step, the DL models were implemented and compared with different activation functions. Among the proposed DL models, the CNN-LSTM architecture has had the best performance. In this architecture, the ReLU activation function with the z-score and L2-combined normalization was used. The proposed CNN-LSTM model has achieved an accuracy percentage of 99.25%, better than the results of most former studies in this field. It is worth mentioning that to perform all simulations, the k-fold cross-validation method with k = 5 has been used.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Shoeibi

Sadeghi

Moridian

et al. 2021

Front. Neuroinform.

107

View full text Add to dashboard Cite

show abstract

“…Deep learning has been applied to various aspects of speech processing, speech recognition, speech and speaker identification and such applications [ 111 ]. In this subsection, we focus on speech source separation applications using variational autoencoders.…”

Section: Applicationsmentioning

confidence: 99%

“…The spectrogram is found by taking the square of the magnitude of the STFT especially for deep learning algorithms involving speech. Typically, in practice, the spectrogram is often normalized before being fed into a neural network [ 111 ]. Alternative inputs include log spectrograms and mel spectrograms.…”

Section: Applicationsmentioning

confidence: 99%

An Overview of Variational Autoencoders for Source Separation, Finance, and Bio-Signal Applications

Singh

Ogunfunmi

2021

Entropy

Self Cite

View full text Add to dashboard Cite

Autoencoders are a self-supervised learning system where, during training, the output is an approximation of the input. Typically, autoencoders have three parts: Encoder (which produces a compressed latent space representation of the input data), the Latent Space (which retains the knowledge in the input data with reduced dimensionality but preserves maximum information) and the Decoder (which reconstructs the input data from the compressed latent space). Autoencoders have found wide applications in dimensionality reduction, object detection, image classification, and image denoising applications. Variational Autoencoders (VAEs) can be regarded as enhanced Autoencoders where a Bayesian approach is used to learn the probability distribution of the input data. VAEs have found wide applications in generating data for speech, images, and text. In this paper, we present a general comprehensive overview of variational autoencoders. We discuss problems with the VAEs and present several variants of the VAEs that attempt to provide solutions to the problems. We present applications of variational autoencoders for finance (a new and emerging field of application), speech/audio source separation, and biosignal applications. Experimental results are presented for an example of speech source separation to illustrate the powerful application of variants of VAE: VAE, β-VAE, and ITL-AE. We conclude the paper with a summary, and we identify possible areas of research in improving performance of VAEs in particular and deep generative models in general, of which VAEs and generative adversarial networks (GANs) are examples.

show abstract

“…The more representative is the deep learning method. It has been recently found that deep learning [17,18] has achieved remarkable success in many speech processing fields with its excellent learning performance. The representative technology is DNN-HMM hybrid structure [19,20], replacing the conventional acoustic modeling based on GMM and HMM.…”

Section: Introductionmentioning

confidence: 99%

An Improved Unsupervised Single‐Channel Speech Separation Algorithm for Processing Speech Sensor Signals

Jiang

Lin

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

As network supporting devices and sensors in the Internet of Things are leaping forward, countless real-world data will be generated for human intelligent applications. Speech sensor networks, an important part of the Internet of Things, have numerous application needs. Indeed, the sensor data can further help intelligent applications to provide higher quality services, whereas this data may involve considerable noise data. Accordingly, speech signal processing method should be urgently implemented to acquire low-noise and effective speech data. Blind source separation and enhancement technique refer to one of the representative methods. However, in the unsupervised complex environment, in the only presence of a single-channel signal, many technical challenges are imposed on achieving single-channel and multiperson mixed speech separation. For this reason, this study develops an unsupervised speech separation method CNMF+JADE, i.e., a hybrid method combined with Convolutional Non-Negative Matrix Factorization and Joint Approximative Diagonalization of Eigenmatrix. Moreover, an adaptive wavelet transform-based speech enhancement technique is proposed, capable of adaptively and effectively enhancing the separated speech signal. The proposed method is aimed at yielding a general and efficient speech processing algorithm for the data acquired by speech sensors. As revealed from the experimental results, in the TIMIT speech sources, the proposed method can effectively extract the target speaker from the mixed speech with a tiny training sample. The algorithm is highly general and robust, capable of technically supporting the processing of speech signal acquired by most speech sensors.

show abstract

A Primer on Deep Learning Architectures and Applications in Speech Processing

Cited by 20 publications

References 55 publications

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

An Overview of Variational Autoencoders for Source Separation, Finance, and Bio-Signal Applications

An Improved Unsupervised Single‐Channel Speech Separation Algorithm for Processing Speech Sensor Signals

Contact Info

Product

Resources

About