Probabilistic space maps for speech with applications
The objective of the proposed research is to develop a probabilistic model of speech production that exploits the multiplicity of mapping between the vocal tract area functions (VTAF) and speech spectra. Two thrusts are developed. In the first, a latent variable model that captures uncertainty in es...
Main Author: | Kalgaonkar, Kaustubh |
---|---|
Published: |
Georgia Institute of Technology
2012
|
Subjects: | |
Online Access: | http://hdl.handle.net/1853/42739 |
Similar Items
-
Multi-Sensor Noise Suppression and Bandwidth Extension for Enhancement of Speech
by: Hu, Rongqiang
Published: (2006) -
Speech Enhancement by MAP Spectral Amplitude Estimation Using a Super-Gaussian Speech Model
by: Lotter Thomas, et al.
Published: (2005-01-01) -
Analysis, synthesis, and recognition of stressed speech
by: Cummings, Kathleen E.
Published: (2007) -
Incorporation of syntax and semantics to improve the performance of an automatic speech recognizer
by: Rapholo, Moyahabo Isaiah
Published: (2013) -
Analysis and compensation of stressed and noisy speech with application to robust automatic recognition
by: Hansen, John H. L.
Published: (2007)