Abstract
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 Deep Belief Networks (DBN) adds any substantial gain over MLPs on the Aurora2 speech recognition task under mismatched noise conditions. Our findings suggest that DBNs outperform single layer MLPs under the clean condition, but the gains diminish as the noise level is increased. Furthermore, using MFCCs in conjunction with the posteriors from DBNs outperforms merely using single DBNs in low to moderate noise conditions. MFCCs, however, do not help for the high noise settings.
Keywords
Deep belief networkComputer sciencePerceptronNoise (video)Artificial intelligenceMultilayer perceptronArtificial neural networkDeep learningSpeech recognitionTask (project management)Pattern recognition (psychology)TandemDeep neural networksHidden Markov modelNoise measurementMachine learningNoise reduction
Affiliated Institutions
Related Publications
Backpropagation training for multilayer conditional random field based phone recognition
Conditional random fields (CRFs) have recently found increased popularity in automatic speech recognition (ASR) applications. CRFs have previously been shown to be effective com...
Deep Belief Networks using discriminative features for phone recognition
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fe...
Boosting attribute and phone estimation accuracies with deep neural networks for detection-based speech recognition
Generation of high-precision sub-phonetic attribute (also known as phonological features) and phone lattices is a key frontend component for detection-based bottom-up speech rec...
Network In Network
Abstract: We propose a novel deep network structure called In Network (NIN) to enhance model discriminability for local patches within the receptive field. The conventional con...
Sparse Multilayer Perceptron for Phoneme Recognition
This paper introduces the sparse multilayer perceptron (SMLP) which jointly learns a sparse feature representation and nonlinear classifier boundaries to optimally discriminate ...
Publication Info
- Year
- 2011
- Type
- article
- Pages
- 4596-4599
- Citations
- 55
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
55
OpenAlex
Cite This
Oriol Vinyals,
Suman Ravuri
(2011).
Comparing multilayer perceptron to Deep Belief Network Tandem features for robust ASR.
, 4596-4599.
https://doi.org/10.1109/icassp.2011.5947378
Identifiers
- DOI
- 10.1109/icassp.2011.5947378