Over the past decades, extensive research has been carried out on various possible implementations of automatic speech recognition (ASR) systems. The most renowned algorithms in the field of ASR are the mel-frequency cepstral coefficients and the hidden Markov models. However, there are also other methods, such as wavelet-based transforms, artificial neural networks and support vector machines, which are becoming more popular. This review article presents a comparative study on different approaches that were proposed for the task of ASR, and which are widely used nowadays.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-spr.2012.0151

Comparative study of automatic speech recognition techniques

Recently great strides have been made in the field of automatic speech recognition (ASR) by using various deep learning techniques. In this study, we present a thorough comparison between cutting-edged techniques currently being used in this area, with a special focus on the various deep learning methods. This study explores different feature extraction methods, state-of-the-art classification models, and vis-a-vis their impact on an ASR. As deep learning techniques are very data-dependent different speech datasets that are available online are also discussed in detail. In the end, the various online toolkits, resources, and language models that can be helpful in the formulation of an ASR are also proffered. In this study, we captured every aspect that can impact the performance of an ASR. Hence, we speculate that this work is a good starting point for academics interested in ASR research.

Automatic speech recognition: a survey

In this paper we discuss the development and implementation of an automated speaker-independent isolated Malay digit speech recognition system. The system is developed using Neuro-Fuzzy approach that combines the human-like reasoning style of fuzzy systems and the learning and connectionist structure of neural networks. To recognize the Malay speech digits, the endpoint detection algorithm is used to trim the silent duration in speech sample, the Mel Frequency Cepstral Coefficient technique is used to extract speech features, the subtractive clustering algorithm is applied to identify the fuzzy inference system, and the Adaptive Neuro Fuzzy Inference System (ANFIS) is used as a modern classification technique to train in identifying the features of speech. The performance of the system was evaluated by using 630 speech samples for training and testing, and experimental results showed that an overall 85.24% recognition rate was achieved.

Isolated Digit Speech Recognition in Malay Language Using Neuro-Fuzzy Approach

Fuzzy modeling require two main steps which are structure identification and parameter optimization, the first one determines the numbers of membership functions and fuzzy if-then rules, while the second identifies a feasible set of parameters under the given structure. However, the increase of input dimension, rule numbers will have an exponential growth and there will cause problem of “rule disaster”. In this paper, we have applied adaptive network fuzzy inference system ANFIS for phonemes recognition. The appropriate learning algorithm is performed on TIMIT speech database supervised type, a pre-processing of the acoustic signal and extracting the coefficients MFCCs parameters relevant to the recognition system. First learning of the network structure by subtractive clustering, in order to define an optimal structure and obtain small number of rules, then learning of parameters network by hybrid learning which combine the gradient decent and least square estimation LSE to find a feasible set of antecedents and consequents parameters. The results obtained show the effectiveness of the method in terms of recognition rate and number of fuzzy rules generated.

/pdf/adaptive-network-based-fuzzy-inference-system-for-speech-5ftx7z8tyk.pdf

Adaptive network based fuzzy inference system for speech recognition through subtractive clustering

Fuzzy classification is the task of partitioning a feature space into fuzzy classes. A Neuro fuzzy classifier with linguistic hedges is proposed for noisy and clean speech classification. The linguistic Hedges are used to improve the meaning of fuzzy rules up to secondary level. Fuzzy entropy is applied to select optimal features of MFCC for framing the rules for designing the fuzzy inference system. Results obtained from the proposed classifier is compared over conventional and Neuro Fuzzy Classifier. The classification rates of the proposed model is better than other traditional and conventional fuzzy classifiers. 0.22 to 5% improved classification accuracy is observed for the FSDD dataset. And 5% to 11% of improved classification accuracy is observed for Kannada dataset. From this study it is identified that LH plays a major role in classifying the overlapped classes of data.

/pdf/a-neuro-fuzzy-classifier-with-linguistic-hedges-for-speech-45iksineoy.pdf

A Neuro Fuzzy Classifier with Linguistic Hedges for Speech Recognition

In this paper we study the feasibility of speech recognition with fuzzy neural Networks for discrete words, dependent or not dependent on speaker. Different Technical methods are used for speech recognition. Most of these methods are based on transfiguration of the speech signals for phonemes and syllables of the words. We use the expression "word Recognition" (because in our proposed method there is no need to catch the phonemes of words.). In our proposed method, Kohonen and LVQ networks are used for compaction and learning the data and then the output is sent to a fuzzy system and a neuro fuzzy system for classifying the conclusion. The experimental results show good precisions. The recognition precision of our proposed method with fuzzy conclusion is 95 percent and with ANFIS conclusion is 96 percent for good data and for all data is 58 percent.

B. H. Helmi

Papers

Speech Recognition with Fuzzy Neural Network for Discrete Words

An Evolutionary Control Model for a Generic Multiagent System Using Artificial Immune Systems