A new hybrid framework based on Hidden Markov models and K-nearest neighbors for speech recognition

Hazmoune, Samira; Bougamouza, Fateh; Mazouzi, Smaine; Bahaj, Mohamed

doi:10.1007/s10772-018-9535-4

Cited by 7 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The K-nearest-neighbor (KNN) algorithm measures [19] the distance between a query scenario and a set of scenarios in the data set. To classify each of the test sample objects, the following operations should be performed sequentially:…”

Section: Knn Algorithmmentioning

confidence: 99%

Voice Identification Using Classification Algorithms

Mamyrbayev¹,

Mekebayev²,

Turdalyuly³

et al. 2020

Intelligent System and Computing

View full text Add to dashboard Cite

This article discusses the classification algorithms for the problem of personality identification by voice using machine learning methods. We used the MFCC algorithm in the speech preprocessing process. To solve the problem, a comparative analysis of five classification algorithms was carried out. In the first experiment, the support vector method was determined-0.90 and multilayer perceptron-0.83, that showed the best results. In the second experiment, a multilayer perceptron with an accuracy of 0.93 was proposed using the Robust scaler method for personal identification. Therefore, to solve this problem, it is possible to use a multi-layer perceptron, taking into account the specifics of the speech signal.

show abstract

Section: Knn Algorithmmentioning

confidence: 99%

Voice Identification Using Classification Algorithms

Mamyrbayev¹,

Mekebayev²,

Turdalyuly³

et al. 2020

Intelligent System and Computing

View full text Add to dashboard Cite

show abstract

“…Reyes et al 25 proposed a start-end gesture recognition method using feature weights in the DTW framework. Hazmoune et al 26 integrated HMM into the K-Nearest Neighbor (KNN) structure to classify the Arabian numerical dataset and showed that the method is effective. Dong et al 27 proposed a method based on hand depth images, this method first uses RF to classify each pixel of the depth image into 11 classes, then uses a hierarchical model search method to calculate the orientation of the joints of each pixel, and finally, the orientation of the joints is input as features into RF for gesture recognition.…”

Section: Rgb Image and Video-based Recognitionmentioning

confidence: 99%

An overview of gesture recognition

et al. 2023

International Conference on Computer Application and Information Security (ICCAIS 2022)

View full text Add to dashboard Cite

With the development of artificial intelligence and human-computer interaction technology, gesture has been widely used in intelligent vehicles, human-computer interaction, virtual reality, and other fields as an important way of communication in people’s daily life. However, there are few review studies that comprehensively evaluate and summarize gesture recognition in recent years. To address this situation, this paper classifies and summarizes the currently used gesture recognition methods. Firstly, the current status of research on static gestures is investigated, followed by an analysis of the progress of research on dynamic gesture recognition, then the commonly used gesture datasets are introduced and their respective characteristics are described, finally, the current challenges and future development trends of gesture recognition are analyzed.

show abstract

“…The characteristics of the KNN algorithm calculates the distance between the feature vectors to be recognized and all stored feature vectors, determining the class most represented among the nearest K feature vectors and storing all the feature vectors, allowing outlier feature vectors to be categorized into other classes [13]. Classifying hijaiyah letters based on their properties is challenging, as letter characteristics exhibit more varied and complex pronunciation patterns than classifications based on letter makhraj or corpus sounds.…”

Section: Introductionmentioning

confidence: 99%

XGBoost and Convolutional Neural Network Classification Models on Pronunciation of Hijaiyah Letters According to Sanad

Azis,

Lestari

2023

join

View full text Add to dashboard Cite

According to Sanad, the pronunciation of Hijaiyah letters can serve as a benchmark for correct or valid reading based on the makhraj and properties of the letters. However, the limited number of Qur'anic Sanad teachers remains one of the obstacles to learning the Qur'an. This study aims to identify the most practical combination of classification models in constructing a voice recognition system that facilitates learning without requiring direct interaction with a teacher. The methods employed include the XGBoost algorithm and CNN. As a result, out of the 12 letter trait labels, the CNN model was utilized for 10 of them, specifically for traits S1, S2, S4, S5, T1, T2, T3, T4, T5, and T6, on trait labels S3 and T7 applying the XGBoost model. Furthermore, the inclusion of additional data yielded performance results for each property, with an average accuracy of 78.14% for property S (letters with opposing properties), 70.69% for property T (letters without opposing properties), and an overall average of 73.79% per letter.

show abstract

A new hybrid framework based on Hidden Markov models and K-nearest neighbors for speech recognition

Cited by 7 publications

References 30 publications

Voice Identification Using Classification Algorithms

Voice Identification Using Classification Algorithms

An overview of gesture recognition

XGBoost and Convolutional Neural Network Classification Models on Pronunciation of Hijaiyah Letters According to Sanad

Contact Info

Product

Resources

About