Context-Dependent MLPs for LVCSR: TANDEM, Hybrid or Both?

38 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning: Methods and Applications (2014, neutral): “Several variants of the DNN-based bottleneck-feature approach have been explored; see details in [16, 137, 201, 285, 308, 368].”
A Primal-Dual Method for Training Recurrent Neural Networks Constrained by the Echo-State Property (2013, methodology): “Finally, our method exploits the DNN features in a very different way than the “tandem” architecture discussed in (T¨uske et al., 2012), where posterior outputs at the top layer of the DNN is concatenated with the acoustic features as new inputs to an HMM system.”
Sequence classification using the high-level features extracted from deep neural networks (2014, background): “Index Terms— deep neural net, feature extraction, ARMA recurrent neural net, phone recognition”
An Overview of Noise-Robust Automatic Speech Recognition (2014, methodology): “…methods, such as zero crossing peak amplitude (ZCPA) [52], average localized synchrony detection (ALSD) [53], perceptual minimum variance distortionless response (PMVDR) [54], power-normalized cepstral coef ﬁ cients (PNCC) [55], invariant-integration features (IIF) [56], amplitude…”
Acoustic Modeling With Hierarchical Reservoirs (2013, background): “However, if there is enough training material, the gains obtained with this approach can be substantial [11], [16], [33].”