A probabilistic approach to AMDF pitch detection

Global error correction routines play an important part in pitch detection algorithms (PDAs). Raw pitch period estimates are often incorrect. A good error correction routine can significantly improve the overall set of pitch estimates for an utterance. A simple and straightforward error correction routine is proposed. The pitch period markers are selected by a two-stage probabilistic postprocessor. A time-domain PDA, AMDF (average magnitude difference function) generates the markers (candidates for the pitch period) for each frame of the utterance. An initial pitch period estimate for each frame is produced, but all of the markers are also saved for possible later use. Using these initial estimates, a probability distribution of the pitch period is calculated across the utterance. This probability distribution is used to adjust the weights of the markers in each frame. Using these new weights, a new pitch period estimate is calculated for each frame. This process is performed twice, each time using the distribution of the previous pitch estimates of the utterance. Initial testing has been done on the CSTR database. The experiments have shown that this procedure can improve the selection of pitch markers and improve pitch contour continuity in the pitch range of the speaker.