Abstract
Bodo Language is phonetically rich language but it is not analysed systematically and scientifically still now. So each and every parts of language is to be studied with the help of modern equipments for find out the accurate results. In the age of Information Technology where the Information Technology (IT) is threading the entire into a Global Village with knowledge as the prime currency and sole differentiator, development of appropriate access technology take part vital role for gaining the information. Especially for India, with its multi-lingual requirements and not so fortunate achievements in terms of overall literacy, development of speech technology in each of its recognized language demands utmost attention. Moreover, development of such Speech Technologies in Indian Languages, with their core dependence on linguistic and cultural ethos, need to be developed largely in India. From the present analysis and study of Bodo vowels spectrograms, it is seen that the lower frequency regions for almost all vowels are very clear. It is a very uncommon characteristic observed in case of the Bodo vowel utterances in comparison with other local languages of Assam. So this will help the speech researcher’s on Bodo Language in various directions in future.
Highlights
The speech signal is a slowly time varying signal
In order to capture the time varying nature of the speech signal, another Fourier Transform, called Short-Time Fourier Transform (STFT) is used. It consists of a separate Fourier Transform on a piece of the waveform under a sliding window, which is represented by w [n, τ], where τ is the position of the window centre and n is the number of sample per window
The spectrograms which are nothing but the squared magnitude of the STFT, plays important role while visualizing the time-varying frequency content of a speech signal
Summary
The speech signal is a slowly time varying signal. When such signals are examined over a sufficiently short period of time, the characteristics of speech signal are fairly stationary; over long periods of time, the signal characteristics change to reflect the different speech sounds being spoken. A single Fourier transform of the entire acoustic signal cannot capture the time varying frequency contents for all the harmonics present. The Short-Time Fourier Transform of the windowed speech waveform, i.e., STFT is given by equation (1): x(ω, τ) = ∑αn=α x[n, τ]exp[−jωn]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
