Machine Learning in Automatic Speech Recognition: A Survey

Padmanabhan, Jayashree; Premkumar, M.

doi:10.1080/02564602.2015.1010611

Cited by 123 publications

(52 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We also apply i) a time delay, randomly selected in [0, 50], to one spectrogram and ii) a perturbation to both of them according to the formula ( ) = Φ( 1 ( ), 1 [ , ] = [1,9]. All these parameters can be chosen by the user, the value here reported are those used in our experiments.…”

Section: Spectrogramemdaaugmenter Applies the Equalized Mixture Data mentioning

confidence: 99%

“…Sound classification and recognition has been included among the pattern recognition tasks for different application domains, e.g. speech recognition [1], music classification [2], environmental sound recognition or biometric identification [3]. In the traditional pattern recognition framework (preprocessing, feature extraction and classification) features have generally been extracted from the actual audio traces (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data augmentation approaches for improving animal audio classification

Nanni

Maguolo

Paci

2020

Ecological Informatics

126

View full text Add to dashboard Cite

In this paper we present ensembles of classifiers for automated animal audio classification, exploiting different data augmentation techniques for training Convolutional Neural Networks (CNNs). The specific animal audio classification problems are i) birds and ii) cat sounds, whose datasets are freely available. We train five different CNNs on the original datasets and on their versions augmented by four augmentation protocols, working on the raw audio signals or their representations as spectrograms. We compared our best approaches with the state of the art, showing that we obtain the best recognition rate on the same datasets, without ad hoc parameter optimization.Our study shows that different CNNs can be trained for the purpose of animal audio classification and that their fusion works better than the stand-alone classifiers. To the best of our knowledge this is the largest study on data augmentation for CNNs in animal audio classification audio datasets using the same set of classifiers and parameters. Our MATLAB code is available at https://github.com/LorisNanni .

show abstract

Section: Spectrogramemdaaugmenter Applies the Equalized Mixture Data mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Data augmentation approaches for improving animal audio classification

Nanni

Maguolo

Paci

2020

Ecological Informatics

126

View full text Add to dashboard Cite

show abstract

“…Moreover, the process through which the ANNs were initialized greatly affect the performance of these networks. Therefore, deep neural networks were preferred for large quantity of unlabeled data [6]. These developments have been listed in Table 1.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The speed in turn depends on the computation times whereas accuracy depends on the percentage of the recognized words. Accuracy is the word recognition rate (WRR), which is given by equation (6) as follows:…”

Section: A Parameters For Checking the Performance Of An Asr Systemmentioning

confidence: 99%

ASR System for Isolated Words using ANN with Back Propagation and Fuzzy based DWT

Mendiratta¹,

Turk²,

Bansal³

2019

IJEAT

View full text Add to dashboard Cite

Speech is the primary means through which human beings interact. Speech has become a way for Man Machine Interaction (MMI). The Speech Recognition (SR) systems have been widely used in smart phones to initiate searches or to type certain text messages, and in control devices to perform switch on or off functions etc. This system comprises three blocks: Pre-processing, Feature Extraction and Classification. The input speech signal is pre-processed to remove the noise and to convert it into a digital form for feature extraction. The feature extraction is a significant process during SR systems design because the features extracted form the basis for accurate recognition of the speech. Only a few features of this signal may be selected for classification purposes. For final recognition of the spoken word or the input signal, various optimization algorithms as classifiers are used. This paper presents an extensive literature review on SR Systems. The authors have attempted to do a brief survey to identify the progress in this field. The survey provides the reader with well-known methods used by previous researchers. It also compares the performance metrics for two ASR techniques developed by the authors. The first technique uses Artificial Neural Network with Back Propagation while the second uses Fuzzy based Discrete Wavelet Transform. It was found that the fuzzy based DWT system provided better results in terms of the performance metrics like accuracy, sensitivity, specificity and word error rate. The paper concludes by providing the reader with a direction of future scope in this research area.

show abstract

“… da íris (Daugman, 2004;Bowyer, Hollingsworth, & Flynn, 2013): uma técnica que se baseia na extração de características da textura da íris; ela é interessante por apresentar 42 boa acurácia; necessita de equipamentos específicos para gerar imagens dos olhos e possui limitações quanto a movimentação da cabeça e da pálpebra;  da face (Parkhi, Vedaldi, & Zisserman, 2015;Jafri & Arabnia, 2009): busca identificar pessoas por diferentes características ligadas a geometria da face e outras particularidades; sua precisão é boa e tem crescido, principalmente com a evolução dos dispositivos fotográficos e das técnicas de modo geral; necessita de dispositivos para capturar imagens e é intrusiva;  da voz (Padmanabhan & Premkumar, 2015): identifica pessoas através do padrão de voz; apresenta boa acurácia em ambientes controlados; porém, pode ter problemas com ruídos sonoros e distância do microfone, além de ser intrusiva;  da digital dos dedos e mãos (Ali, Mahale, Yannawar, & Gaikwad, 2016;Maio, Maltoni, Cappelli, Wayman, & Jain, 2002): o reconhecimento de digitais é amplamente utilizado; possui boa acurácia, porém, necessita de hardware específico para capturar as digitais.…”

Section: Reconhecimento De Usuáriounclassified

Dinâmica da Digitação Aplicada à Autenticação Periódica de Usuários em Ambientes Virtuais de Aprendizagem

Cruz

Duarte

Goldschmidt

2017

RBIE

View full text Add to dashboard Cite

Resumo A autenticação de usuário nos ambientes virtuais de aprendizagem (AVAs) existentes é, em geral, pontual e intrusiva, ocorrendo no momento em que o usuário Abstract The authentication of users on a Virtual Learning Environment (VLE) is, in general, punctual and intrusive, occurring when the user connects to the environment, by typing his password. Such approach allows, after the initial login, that unauthenticated users take the role of authenticated users and perform tasks in the environment, causing, among other things, distortions in the perception about the academic performance of students. The objective of this work is, thus, to propose a mechanism to execute periodic and non-intrusive authentications of users in VLEs.The proposed mechanism uses machine learning techniques to build recognition models based on the keystroke dynamics of users and it is also independent of the used VLE. A prototype of the proposed mechanism, integrated with Moodle, was implemented and applied to a postgraduate course with seventeen users. The recognition models generated by the prototype in the case study showed a performance above 92% of accuracy, which is a positive indication about the viability of the utilization of the proposed mechanism.

show abstract

Machine Learning in Automatic Speech Recognition: A Survey

Cited by 123 publications

References 40 publications

Data augmentation approaches for improving animal audio classification

Data augmentation approaches for improving animal audio classification

ASR System for Isolated Words using ANN with Back Propagation and Fuzzy based DWT

Dinâmica da Digitação Aplicada à Autenticação Periódica de Usuários em Ambientes Virtuais de Aprendizagem

Contact Info

Product

Resources

About