Time-varying quasi-closed-phase analysis for accurate formant tracking in speech signals

Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2020-06-04

Major/Subject

Mcode

Degree programme

Language

en

Pages

14

Series

IEEE/ACM Transactions on Audio, Speech, and Language Processing, Volume 28, pp. 1901-1914

Abstract

In this paper, we propose a new method for the accurate estimation and tracking of formants in speech signals using time-varying quasi-closed-phase (TVQCP) analysis. Con-ventional formant tracking methods typically adopt a two-stage estimate-and-track strategy wherein an initial set of formant candidates are estimated using short-time analysis (e.g., 10–50 ms), followed by a tracking stage based on dynamic programming or a linear state-space model. One of the main disadvantages of these approaches is that the tracking stage, however good it may be, cannot improve upon the formant estimation accuracy of the first stage. The proposed TVQCP method provides a single-stage formant tracking that combines the estimation and tracking stages into one. TVQCP analysis combines three approaches to improve formant estimation and tracking: (1) it uses temporally weighted quasi-closed-phase analysis to derive closed-phase es-timates of the vocal tract with reduced interference from the excitation source, (2) it increases the residual sparsity by using the L1 optimization and (3) it uses time-varying linear prediction analysis over long time windows (e.g., 100–200 ms) to impose a continuity constraint on the vocal tract model and hence on the formant trajectories. Formant tracking experiments with a wide variety of synthetic and natural speech signals show that the proposed TVQCP method performs better than conventional and popular formant tracking tools, such as Wavesurfer and Praat (based on dynamic programming), the KARMA algorithm (based on Kalman filtering), and DeepFormants (based on deep neural networks trained in a supervised manner).

Description

Keywords

Time-varying linear prediction, weighted linear prediction, quasi-closed-phase analysis, formant tracking

Other note

Citation

Gowda, D, Kadiri, S, Story, B & Alku, P 2020, ' Time-varying quasi-closed-phase analysis for accurate formant tracking in speech signals ', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, 9108548, pp. 1901-1914 . https://doi.org/10.1109/TASLP.2020.3000037