417 search results - page 51 / 84 » Signal processing tools for speech recognition |
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
This paper introduces a discriminative extension to whole-word point process modeling techniques. Meant to circumvent the strong independence assumptions of their generative prede...
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
The outputs of multi-layer perceptron (MLP) classifiers have been successfully used in tandem systems as features for HMM-based automatic speech recognition. In a previous paper, ...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
Research in the speaker recognition community has continued to address methods of mitigating variational nuisances. Telephone and auxiliary-microphone recorded speech emphasize th...
ICASSP
2009
IEEE
14 years 2 months ago
2009
IEEE
Maximum-Likelihod Linear Regression (MLLR) transform coefficients have shown to be useful features for text-independent speaker recognition systems. These use MLLR coefficients ...
ACL
2012
11 years 10 months ago
2012
Long-span features, such as syntax, can improve language models for tasks such as speech recognition and machine translation. However, these language models can be difficult to u...