HMM-Based Reconstruction of Unreliable Spectrographic Data for Noise Robust Speech Recognition

This paper presents a framework for efficient HMM-based estimation of unreliable spectrographic speech data. It discusses the role of Hidden Markov Models (HMMs) during minimum mean-square error (MMSE) spectral reconstruction. 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 mapping 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 steady-state and transitional statistics. Adaptation of observation statistics are derived from stochastic...

• Type: Journal
• Year: 2010
• Where: TASLP
• Authors: Bengt J. Borgstrom, Abeer Alwan
• Keywords: Efficient Hmm-based Estimation, HMM-based Reconstruction, Lower Resolution, Software Engineering, TASLP 2010