Pitch and formant estimation of bangla speech signal using autocorrelation, cepstrum and LPC algorithm
Muhammad Navid Anjum Aadit, Sharadindu Gopal Kirtania, Mehnaz Tabassum Mahin · 2016
In this paper, we present comparative study of digital speech processing on Bangla speech signal. We represent oral characteristics of Bangla alphabet in terms of pitch and formant. We worked with both vowels and consonants to show their difference in practical use. We take oral speech signals as voice record and extract phonemes to analyze in both time and frequency domains. Both male and female voices are included in the analysis to find the effect of gender on Bangla voice speech. We verify our work by showing similarity of the results in time and frequency domains. We calculate first three formants of Bangla phonemes to show their relative impacts on Bangla speech. This extensive study of Bangla speech would provide listed information and data for further research to extract some other important features in this field.