| | |
Summary: 1
HMM-Based Reconstruction of Unreliable
Spectrographic Data for Noise Robust Speech
Recognition
Bengt J. Borgstršom, Student Member, IEEE, and Abeer Alwan, IEEE Fellow
Abstract-- This paper presents a framework for efficient
HMM-based estimation of unreliable spectrographic speech data.
It discusses the role of Hidden Markov Models (HMMs) dur-
ing minimum mean-square error (MMSE) spectral reconstruc-
tion. We develop novel HMM-based reconstruction algorithms
which exploit intra-channel (across-time) correlation and/or
inter-channel (across-frequency) correlation. For the sake of
computational efficiency, this paper utilizes approximations to
HMM-based decoding methods by developing models constructed
from lower resolution quantizers. State configurations for lower
resolution models are obtained through a tree-structured map-
ping of quantizer centroids, and model parameters are adapted
accordingly. HMM downsampling avoids expensive re-training
of models, and eliminates unnecessary memory requirements.
Explicit general formulae are presented for the adaptation of
|
