2011
DOI: 10.1109/tasl.2010.2050513
|View full text |Cite
|
Sign up to set email alerts
|

Data Balancing for Efficient Training of Hybrid ANN/HMM Automatic Speech Recognition Systems

Abstract: Abstract-Hybrid speech recognizers, where the estimation of the emission pdf of the states of Hidden Markov Models (HMMs), usually carried out using Gaussian Mixture Models (GMMs), is substituted by Artificial Neural Networks (ANNs) have several advantages over the classical systems. However, to obtain performance improvements, the computational requirements are heavily increased because of the need to train the ANN.Departing from the observation of the remarkable skewness of speech data, this paper proposes s… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
21
0

Year Published

2012
2012
2022
2022

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 22 publications
(21 citation statements)
references
References 41 publications
0
21
0
Order By: Relevance
“…The problem of obtaining scaled likelihoods from a posteriori probabilities in the hybrid ANN/HMM context was an open issue since mismatches between the a priori probabilities of the training and test databases led to inconsistent results [1], [4], [20], [63], [65], [66]. In [5] it is shown that scaled likelihoods should always be estimated using the prior probabilities from the training data. In our case, the balancing of the training set enables the interpretation of the outputs of the SVM as scaled likelihoods without the need of applying any corrections.…”
Section: Data Selection and Balancingmentioning
confidence: 99%
See 2 more Smart Citations
“…The problem of obtaining scaled likelihoods from a posteriori probabilities in the hybrid ANN/HMM context was an open issue since mismatches between the a priori probabilities of the training and test databases led to inconsistent results [1], [4], [20], [63], [65], [66]. In [5] it is shown that scaled likelihoods should always be estimated using the prior probabilities from the training data. In our case, the balancing of the training set enables the interpretation of the outputs of the SVM as scaled likelihoods without the need of applying any corrections.…”
Section: Data Selection and Balancingmentioning
confidence: 99%
“…In this work, the first problem is alleviated by randomly selecting a balanced subset of training samples, which significantly reduces the computational cost of the training process while causing negligible reduction in performance, as it was previously demonstrated in the ANN/HMM paradigm [5]. However, further research on this issue is required for the proposed system to manage more demanding ASR tasks.…”
Section: Introductionmentioning
confidence: 98%
See 1 more Smart Citation
“…The learning algorithm can be the conventional backpropagation [18], or a more sophisticated variation of it [2]. In the learning phase, the desired output is 1 for the correct and 0 for all other speech units.…”
Section: Connectionnist Models For Recognitionmentioning
confidence: 99%
“…This important research finding eased their integration with the HMM current state of the art recognition system technology [2]. This fact led to the possibility of unifying HMM and ANN within unifying novel models [5].…”
Section: Introductionmentioning
confidence: 97%