DeepAI
Log In Sign Up

Unsupervised Classification of Voiced Speech and Pitch Tracking Using Forward-Backward Kalman Filtering

03/01/2021
by   Benedikt Boenninghoff, et al.
0

The detection of voiced speech, the estimation of the fundamental frequency, and the tracking of pitch values over time are crucial subtasks for a variety of speech processing techniques. Many different algorithms have been developed for each of the three subtasks. We present a new algorithm that integrates the three subtasks into a single procedure. The algorithm can be applied to pre-recorded speech utterances in the presence of considerable amounts of background noise. We combine a collection of standard metrics, such as the zero-crossing rate, for example, to formulate an unsupervised voicing classifier. The estimation of pitch values is accomplished with a hybrid autocorrelation-based technique. We propose a forward-backward Kalman filter to smooth the estimated pitch contour. In experiments, we are able to show that the proposed method compares favorably with current, state-of-the-art pitch detection algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/07/2017

Phase-Aware Single-Channel Speech Enhancement with Modulation-Domain Kalman Filtering

We present a single-channel phase-sensitive speech enhancement algorithm...
07/23/2022

Low-Complexity Acoustic Echo Cancellation with Neural Kalman Filtering

The Kalman filter has been adopted in acoustic echo cancellation due to ...
07/26/2018

Modulation-Domain Kalman Filtering for Monaural Blind Speech Denoising and Dereverberation

We describe a monaural speech enhancement algorithm based on modulation-...
10/27/2022

A Fast and Accurate Pitch Estimation Algorithm Based on the Pseudo Wigner-Ville Distribution

Estimation of fundamental frequency (F0) in voiced segments of speech si...
12/06/2018

Joint Target Detection, Tracking and Classification with Forward-Backward PHD Smoothing

Forward-backward Probability Hypothesis Density (PHD) smoothing is an ef...
04/23/2018

Layered Based Augmented Complex Kalman Filter for Fast Forecasting-Aided State Estimation of Distribution Networks

In the presence of renewable resources, distribution networks have becom...