No abstract

No abstract

A high degree of robustness is a prerequisite to operate speech and language processing systems in practical environments. Performance of these systems is highly influenced by varying and mixed background environments. In this paper, we put forward a robust method for automatic language identification in various background environments. Combined temporal and spectral processing method is used as a preprocessing technique for enhancing the degraded speech. Language discriminative information in high sonority regions of speech is used for the task of language identification. Sonority regions are regions of speech whose signal energy is high and these regions are less influenced by background environments. Spectral energy of formants in the glottal closure regions is employed as an acoustic correlate for the detection of sonority regions of speech. In this paper performance of the LID system is studied in various background environments like clean room, car factory,high frequency,pink and white noise environments. In this work, Indian Institute of Technology Kharagpur -Multi Lingual Indian Language Speech Corpus (IITKGP-MLILSC) is used for building language identification system. Noise speech samples from the NOISEX database are employed in the present study. The performance of the proposed method is quite satisfactory compared to existing approaches.

Defocus blur is to a great degree regular in images caught utilizing optical imaging frameworks. It might be bothersome, however may likewise be a deliberate imaginative impact, in this manner it can either upgrade or hinder our visual view of the image scene. For assignments, for example, image restoration and object recognition, one should need to portion an in part blurred image into blurred and non-blurred areas. In this paper, we propose sharpness metric in light of local binary patterns and a hearty segmentation calculation to isolate all through focus image districts. The proposed sharpness metric adventures the perception that most local image fixes in blurry areas have altogether less of certain local binary patterns contrasted and those in sharp districts. Utilizing this metric together with image tangling and multiscale surmising, we got excellent sharpness maps. Tests on several halfway blurred images were utilized to assess our blur segmentation calculation and six comparator techniques. The outcomes demonstrate that our calculation accomplishes similar segmentation comes about with the best in class and have enormous speed advantage over the others. in Extension we are using LLBP (Line Local Binary Pattern ) for getting better output in blur images.

No abstract