Sixth European Conference on Speech Communication and Technology
(EUROSPEECH'99)

Budapest, Hungary
September 5-9, 1999

Unified Decoding and Feature Representation for Improved Speech Recognition

Li Jiang, Xuedong Huang

Microsoft Research, Redmond, WA, USA

In this paper we propose a unified framework for decoding and feature representation based on the Maximum A Posterior (MAP) principle. The search space is augmented with an additional feature stream dimension such that different feature repre-sentations can be utilized for different phonetic context under the HMM decoding framework. We also provide a theoretic explanation for the unified framework. It gives us ôsupervised" signal processing and feature extraction for the recognition system, which has reduced the word recognition error rate by 15% on a large-vocabulary continuous speech recognition task when multiple feature streams are used simultaneously.


Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Jiang, Li / Huang, Xuedong (1999): "Unified decoding and feature representation for improved speech recognition", In EUROSPEECH'99, 1331-1334.