Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM
Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing2008pp. 3925–3928
Citations Over TimeTop 14% of 2008 papers
Abstract
In this paper, we describe a novel statistical approach to the vocal tract transfer function (VTTF) estimation of a speech signal based on a factor analyzed trajectory hidden Markov model (HMM). Because speech is a quasi-periodic signal, there are many missing frequency components between adjacent F 0 harmonics. The proposed method determines a time-varying VTTF sequence based on the maximum a posteriori (MAP) estimation considering not only harmonic components observed at each analyzed frame but also those at other frames for stochastically interpolating the missing frequency parts.
Related Papers
- → Vocal tract length perturbation and its application to male-female vocal tract shape conversion(2007)16 cited
- → SIMULATION OF VOCAL TRACT GROWTH FOR ARTICULATORY SPEECH SYNTHESIS(2007)12 cited
- → Analysis for the extraction of phonological information using the vocal tract area(2013)2 cited
- → Acoustic vocal tract model of one-year-old children(2014)1 cited
- → Formant frequencies for incrementally varying vocal tract(1978)