Title | ||
---|---|---|
Deep Neural Network Based Continuous Speech Recognition for Serbian Using the Kaldi Toolkit. |
Abstract | ||
---|---|---|
This paper presents a deep neural network (DNN) based large vocabulary continuous speech recognition (LVCSR) system for Serbian, developed using the open-source Kaldi speech recognition toolkit. The DNNs are initialized using stacked restricted Boltzmann machines (RBMs) and trained using cross-entropy as the objective function and the standard error backpropagation procedure in order to provide posterior probability estimates for the hidden Markov model (HMM) states. Emission densities of HMM states are represented as Gaussian mixture models (GMMs). The recipes were modified based on the particularities of the Serbian language in order to achieve the optimal results. A corpus of approximately 90 hours of speech (21000 utterances) is used for the training. The performances are compared for two different sets of utterances between the baseline GMM-HMM algorithm and various DNN settings. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/978-3-319-23132-7_23 | Lecture Notes in Artificial Intelligence |
Keywords | Field | DocType |
Kaldi speech recognition toolkit,Continuous speech recognition,Deep neural networks,Serbian | Boltzmann machine,Pattern recognition,Serbian,Computer science,Speech recognition,Posterior probability,Artificial intelligence,Backpropagation,Artificial neural network,Hidden Markov model,Vocabulary,Mixture model | Conference |
Volume | ISSN | Citations |
9319 | 0302-9743 | 4 |
PageRank | References | Authors |
0.48 | 7 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Branislav M. Popovic | 1 | 96 | 17.13 |
Stevan Ostrogonac | 2 | 9 | 1.40 |
Edvin Pakoci | 3 | 10 | 3.02 |
Nikša Jakovljević | 4 | 28 | 4.11 |
Vlado Delić | 5 | 52 | 12.26 |