Computer Systems Engineering

This paper describes formant based Pashto continuous speech syn-thesizer, which automatically generates the Pashto Speech from given text using formants. In this work, initially some samples of Pashto Speech are recorded in a noise free environment by using the Sony PCM-M 10 linear Recorder device. The recorded Pashto continuous speech audio file are then split into isolated Pashto sentences, using the Adobe Audition ver 1.0. After splitting the entire continuous Pashto audio file into isolated sentences the features from these iso-lated Pashto sentences have been extracted by utilizing the colea tool. Pashto speech sentences from given text are then synthesized through formant tech-nique by utilizing the features extracted from the isolated Pashto audio files.

In this paper, the objective is image classification analysis based on the well known image descriptors, the Scale Invariant Feature Transform (SIFT) and the Speeded up Robust Features (SURF) on five online available standard datasets. For the classification framework, we adopted the visual words approach. For SIFT, we use the Lowe’s implementation and for Speeded up Robust Features (SURF), the Herbert Bay’s implementation is used. Extensive experimentation using five datasets shows that SURF is a better choice compared to Scale Invariant Feature Transform (SIFT).

Language resources for Urdu language are not well developed. In this work, we summarize our work on the development of Urdu speech corpus for isolated words. The Corpus comprises of 250 isolated words of Urdu recorded by ten individuals. The speakers include both native and non-native, male and female individuals. The corpus can be used for both speech and speaker recognition tasks. We also report our results on automatic speech recognition task for the said corpus. The framework extracts Mel Frequency Cepstral Coefficients along with the velocity and acceleration coefficients, which are then fed to different classifiers to perform recognition task. The classifiers used are Support Vector Machines, Random Forest and Linear Discriminant Analysis. Experimental results show that the best results are provided by the Support Vector Machines with a test set accuracy of 73%. The results reported in this work may provide a useful baseline for future research on automatic speech recognition of Urdu.