PRAAT Software; Utilization of Computerized Approach for Determination of Variation Present in Recorded Audios from Distinct Sources

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2019 by IJETT Journal
Volume-67 Issue-3
Year of Publication : 2019
Authors : Smriti Rawat, Tasbiha Khan, Dr Amit Chauhan
  10.14445/22315381/IJETT-V67I3P221

MLA 

MLA Style: Smriti Rawat, Tasbiha Khan, Dr Amit Chauhan "PRAAT Software; Utilization of Computerized Approach for Determination of Variation Present in Recorded Audios from Distinct Sources" International Journal of Engineering Trends and Technology 67.3 (2019): 111-114.

APA Style: Smriti Rawat, Tasbiha Khan, Dr Amit Chauhan (2019). PRAAT Software; Utilization of Computerized Approach for Determination of Variation Present in Recorded Audios from Distinct Sources. International Journal of Engineering Trends and Technology, 67(3), 111-114.

Abstract
In Forensic Field, various sources of evidences play a vital role to establish a link between the crime, preparator and the victim. These types of evidences which might be in physical form or material quality, any tangible article, biological form of evidences or chemical etc. Physical evidence is any evidence that have physical or material quality, a tangible article no matter whether microscopic or macroscopic. It encompasses all objects, living or inanimate; solid-, liquid, or gas. Among these physical evidences i.e. fingerprints, palm prints hair strands, blood etc. there is an important class of physical evidences which is audio evidences.Audio forensics involves acquisition, analysis, and evaluation of audio recordings that may eventually be presented as admissible evidence in the court of law. These audio recordings may turn out to be very important evidences in the field of forensic science. They can be encountered most frequently in the cases of ransom calls, cybercrimes, lost and found cases, etc. They may be available from the emergency call helpline, telephone answering machines, voicemail recording, cell phones and computer files. This study was carried out to analyze the authenticity of recoded audios of an individual by various modes of recordings. As a resultant of this study, it was observed that distinct mode of recordings affects the quality of recoding required a repair before the conclusion. This study can be helpful to determine the time duration of recorded audio based on intensity and the length of pitch.

Reference
[1] K. Walker and S. Strassel, “The RATS radio traffic collection system,” in ISCA Speaker Odyssey, 2012.
[2] Tim Ng, Bing Zhang, Long Nguyen, Spyros Matsoukas, Karel Vesely, Pavel Matˇejka, Xinhui Zhu, and NimaMesgarani, “Developing a speech activity detection system for the darparats program,” in Proc. of Interspeech 2012, Sept. 2012.
[3] H. Hermansky, “RASTA processing of speech,” IEEE Trans. Speech and Audio Processing, vol. 2, pp. 578–589, 1994.
[4] Z. Tan and B. Lindbeg, “Low-complexity variable frame rate analysis for speech recognition and voice activity detection,” Journal of Selected Topics in Signal Processing, pp. 798–807, 2010.
[5] P. Boersma and D. Weenik, “Praat: doing phonetics by computer (v. 5.1.05),” http://www.praat.org.
[6] Rainer Martin, “Noise power spectral density estimation based on optimal smoothing and minimum statistics,” IEEE Transactions on Speech and Audio Processing, vol. 9, no. 5, pp. 504– 512, 2001.
[7] S. Sridharan J. Pelecanos, “Feature warping for robust speaker verification,” in Proceedings of Odyssey 2006: The Speaker and Language Recognition Workshop, 2006, pp. 213–218.
[8] Qi Li and Yan Huang, “Robust speaker identification using an auditory-based feature,” in Proc. of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2010, pp. 4514–4517.
[9] R. Kumerasan and A. Rao, “Model-based approach to envelope and positive instantaneous frequency estimation of signals with speech applications,” JASA, vol. 105, pp. 1912–1924, 1999.
[10] M. Athineos and D. Ellis, “Autoregressive modelling of temporal envelopes,” IEEE.
[11] Ayushi Sharma, Ajit Singh, Implementation of 16X16 bit and 32X32 bit vedic multiplier using FPGA board. International journal of engineering trends and technology. Vol 42 (1) 2016, Pg; 1-5.
[12] G. Sonia, T. Murli Mohan. An efficient multi keyword search with integrated model. International journal of engineering trends and technology. Vol 40 (4) 2016, Pg; 210-214.

Keywords
Recorded audio, evidences, computerized approach, variation, software etc.