Database development and automatic speech recognition of isolated Pashto spoken digits using MFCC and K-NN

Abstract

Automatic recognition of isolated spoken digits is one of the most challenging tasks in the area of Automatic Speech Recognition. In this paper, Database Development and Automatic Speech Recognition of Isolated Pashto Spoken Digits from Sefer (0) to Naha (9) has been presented. A number of 50 individual Pashto native speakers (25 male and 25 female) of different ages, ranging from 18 to 60 years, were involved to utter from Sefer (0) to Naha (9) digits separately. Sony PCM-M 10 linear recorder is used for recoding purpose in the office and home in noise free environment. Adobe audition version 1.0 is used to split the audio of digits into individual digits and result is saved in .wav format. Mel frequency cepstral coefficients is used to extract speech features. K nearest neighbor classifier is used for the first time up to author knowledge in Pashto language to classify the features of speech and compare its accuracy with linear discriminate analysis. The experimental results are evaluated, and the overall average recognition exactitude of 76.8 % is obtained.

Prediction of Recombination Spots Using Novel Hybrid Feature Extraction Method via Deep Learning Approach

“…K-nearest neighbor (KNN) (or Lazy learning) algorithm is a popular algorithm used for both classification and regression purposes (Hu et al, 2016 ). However, it is mostly used for classification problems (Ali et al, 2015 ; Zuo et al, 2015 ; Khan et al, 2017 ). KNN is an instance-based and non-parametric learning algorithm and can be considered a simple machine learning algorithm (Donaldson, 1967 ; Qin et al, 2013 ).…”

Identification of Heat Shock Protein families and J-protein types by incorporating Dipeptide Composition into Chou's general PseAAC

“…K-nearest neighbor (KNN) is the most popular classification algorithm also called Lazy learning algorithm [62,63]. This algorithm is mostly applied in data mining, image processing, speech recognition, statistics, machine learning and bioinformatics [62,64,65].…”

“…This algorithm is mostly applied in data mining, image processing, speech recognition, statistics, machine learning and bioinformatics [62,64,65]. KNN has achieved substantial performance compared to many other learning algorithms [42].…”

Pashto isolated digits recognition using deep convolutional neural network

“…Working on ASR has started about half century ago for English language but development of ASR for local languages is a new trend, emerged in the last few decades which opens the door for layman to interact with computer in friendly manner. Thus, native speakers [4], can communicate with computer through speech in their own regional languages. The development of an ASR for local languages is quite a challenging task due to the lack of resources such as corpus with enough vocabulary, dialectical variation and so on.…”

“…Many works have been done for local languages such as in Punjabi (spoken in Pakistan and India) [5,6,7], Gujrati (local language of India) [8], Urdu (national language of Pakistan and forth most widely spoken language in the world) [9,10,11,12,13], Hindi (an official language of India) [1,14,15,16], Marathi (spoken in India) [17], Arabic (an official language of Arab and fifth widely used language in the world) [18,19], Bengali (spoken language of Bangladesh) [20]. The current work also includes Pashto language but very little works has been done in the development of Pashto speech recognition system [4]. Fortunately, Pashto share some characteristics with other languages like Arabic, Urdu and Persian languages.…”