large-vocabulary speech recognition

NAACL
1994

114views Computational Linguistics» more NAACL 1994»

High-Accuracy Large-Vocabulary Speech Recognition Using Mixture Tying and Consistency Modeling

14 years 25 days ago

Improved acoustic modeling can significantly decrease the error rate in large-vocabulary speech recognition. Our approach to the problem is twofold. We first propose a scheme that...

Vassilios Digalakis, Hy Murveit

claim paper

Read More »

click to vote

ICASSP
2008
IEEE

125views Signal Processing» more ICASSP 2008»

Corrected tandem features for acoustic model training

14 years 6 months ago

Download www.icsi.berkeley.edu

This paper describes a simple method for signiﬁcantly improving Tandem features used to train acoustic models for large-vocabulary speech recognition. The linear activations at ...

Arlo Faria, Nelson Morgan

claim paper

Read More »

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers