Sciweavers

9 search results - page 1 / 2
» Posterior features for template-based ASR
Sort
View
ICASSP
2011
IEEE
12 years 9 months ago
Posterior features for template-based ASR
This paper investigates the use of phoneme class conditional probabilities as features (posterior features) for template-based ASR. Using 75 words and 600 words task-independent a...
Serena Soldo, Mathew Magimai-Doss, Joel Pinto, Her...
ICASSP
2011
IEEE
12 years 9 months ago
Comparing multilayer perceptron to Deep Belief Network Tandem features for robust ASR
In this paper, we extend the work done on integrating multilayer perceptron (MLP) networks with HMM systems via the Tandem approach. In particular, we explore whether the use of D...
Oriol Vinyals, Suman V. Ravuri
NAACL
2007
13 years 6 months ago
Joint Versus Independent Phonological Feature Models within CRF Phone Recognition
We compare the effect of joint modeling of phonological features to independent feature detectors in a Conditional Random Fields framework. Joint modeling of features is achieved ...
Ilana Bromberg, Jeremy Morris, Eric Fosler-Lussier
ICASSP
2010
IEEE
13 years 5 months ago
Analysis of phone posterior feature space exploiting class-specific sparsity and MLP-based similarity measure
Class posterior distributions have recently been used quite successfully in Automatic Speech Recognition (ASR), either for frame or phone level classification or as acoustic featu...
Afsaneh Asaei, Benjamin Picart, Hervé Bourl...
MLMI
2007
Springer
13 years 11 months ago
A Study of Phoneme and Grapheme Based Context-Dependent ASR Systems
In this paper we present a study of automatic speech recognition systems using context-dependent phonemes and graphemes as sub-word units based on the conventional HMM/GMM system a...
John Dines, Mathew Magimai-Doss