Abstract
This paper focuses on the speech signals decomposition problem based on three sinusoidal models which can be viewed as three versions of a basic model: the Harmonic plus Noise Model, HNM. For the first model, noted as HNM/sub 1/, the harmonic amplitudes are retained constants within the analysis frame; the phase is assumed to be linear. The second model, HNM/sub 2/, makes use of linearly varying complex amplitudes for the harmonic part whereas, the third model, HNM/sub 3/, makes use of a third order polynomial with real coefficients for the harmonic amplitudes and also linear phase as the first model. To obtain the non-periodic part (or noise part) the harmonic part is simply subtracting from the original speech signal in the time domain.
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.
