Maximum likelihood pitch estimation using sinusoidal modeling
Vijay S. Mahadevan, Carol Espy-Wilson · 2011
An algorithm for optimal estimation of pitch frequency using a maximum likelihood formulation is presented. The speech waveform is modeled using sinusoidal basis functions that are harmonically tied together to explicitly capture the periodic structure of voiced speech. The problem of pitch estimation is casted as a model selection problem and the Akaike Information Criterion is used to estimate the pitch.