A novel filtering-based F0 estimation algorithm with an application to voice conversion

We propose a novel F
₀
estimation algorithm that initially estimates the glottal closure instants (GCIs) or pitch and then computes the corresponding fundamental frequency (F
₀
). The proposed method eliminates the assumption that F
₀
is constant over a segment of short duration (i.e., 20-30 ms). We use our previously proposed novel filtering-based approach for GCI estimation. As the proposed method directly operates on the entire speech signal, it does not require to set the window length and thus, it is free from the problem of spectral leakage. Measuring the effectiveness of proposed F
₀
estimation algorithm w.r.t. three state-of-the-art methods, namely, Yet Another Algorithm for Pitch tracking (YAAPT), Speech Transformation and Representation using Adaptive Interpolation of weiGHT spectrum (STRAIGHT) and Pitch Detection Algorithm (PDA), is challenging in the absence of the ground truth. Since accurate estimation of F
_o
will impact the quality of converted voice in Voice Conversion (VC) task. Hence, we measure the effectiveness F
_o
estimation algorithm in the application of VC task. The quality and speaker similarity of the converted voice have been evaluated using two subjective measures, namely, Mean Opinion Scores (MOS) and ABX test, respectively.