Deep convolutional neural networks for LVCSR

  title={Deep convolutional neural networks for LVCSR},
  author={Tara N. Sainath and Abdel-rahman Mohamed and Brian Kingsbury and Bhuvana Ramabhadran},
  journal={2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
Convolutional Neural Networks (CNNs) are an alternative type of neural network that can be used to reduce spectral variations and model spectral correlations which exist in signals. [] Key Method Specifically, we focus on how many convolutional layers are needed, what is the optimal number of hidden units, what is the best pooling strategy, and the best input feature type for CNNs. We then explore the behavior of neural network features extracted from CNNs on a variety of LVCSR tasks, comparing CNNs to DNNs…

Figures and Tables from this paper

Improvements to Deep Convolutional Neural Networks for LVCSR

A deep analysis comparing limited weight sharing and full weight sharing with state-of-the-art features is conducted and an effective strategy to use dropout during Hessian-free sequence training is introduced.

Very deep multilingual convolutional neural networks for LVCSR

A very deep convolutional network architecture with up to 14 weight layers, with small 3×3 kernels, inspired by the VGG Imagenet 2014 architecture is introduced and multilingual CNNs with multiple untied layers are introduced.

An analysis of convolutional neural networks for speech recognition

  • J. HuangJinyu LiY. Gong
  • Computer Science
    2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2015
By visualizing the localized filters learned in the convolutional layer, it is shown that edge detectors in varying directions can be automatically learned and it is established that the CNN structure combined with maxout units is the most effective model under small-sizing constraints for the purpose of deploying small-footprint models to devices.

Phone recognition with hierarchical convolutional deep maxout networks

  • L. Tóth
  • Computer Science
    EURASIP J. Audio Speech Music. Process.
  • 2015
It is shown that with the hierarchical modelling approach, the CNN can reduce the error rate of the network on an expanded context of input, and it is found that all the proposed modelling improvements give consistently better results for this larger database as well.

Advanced Convolutional Neural Network-Based Hybrid Acoustic Models for Low-Resource Speech Recognition

The results of contributions to combine CNN and conventional RNN with gate, highway, and residual networks to reduce the above problems are presented and the optimal neural network structures and training strategies for the proposed neural network models are explored.

Convolutional Neural Networks for Speech Recognition

It is shown that further error rate reduction can be obtained by using convolutional neural networks (CNNs), and a limited-weight-sharing scheme is proposed that can better model speech features.

A Hybrid of Deep CNN and Bidirectional LSTM for Automatic Speech Recognition

A hybrid architecture of CNN-BLSTM is proposed to appropriately use spatial and temporal properties of the speech signal and to improve the continuous speech recognition task and overcome another shortcoming of CNN, i.e. speaker-adapted features, which are not possible to be directly modeled in CNN.

Advances in Very Deep Convolutional Neural Networks for LVCSR

This paper proposes a new CNN design without timepadding and without timepooling, which is slightly suboptimal for accuracy, but has two significant advantages: it enables sequence training and deployment by allowing efficient convolutional evaluation of full utterances, and, it allows for batch normalization to be straightforwardly adopted to CNNs on sequence data.

Convolutional Neural Network for ASR

  • Sourav NewatiaR. Aggarwal
  • Computer Science
    2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA)
  • 2018
This paper aims to provide a broad survey on different types of pooling techniques applied in CNNs architecture, including key properties of CNNs, architecture ofCNNs, and summarize the improvements of CNN’s.



Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition

The proposed CNN architecture is applied to speech recognition within the framework of hybrid NN-HMM model to use local filtering and max-pooling in frequency domain to normalize speaker variance to achieve higher multi-speaker speech recognition performance.

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

A pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output that can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs.

Face recognition: a convolutional neural-network approach

A hybrid neural-network for human face recognition which compares favourably with other methods and analyzes the computational complexity and discusses how new classes could be added to the trained recognizer.

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

This article provides an overview of progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.

Deep Neural Networks for Acoustic Modeling in Speech Recognition

This paper provides an overview of this progress and repres nts the shared views of four research groups who have had recent successes in using deep neural networks for a coustic modeling in speech recognition.

Auto-encoder bottleneck features using deep belief networks

The experiments indicate that with the AE-BN architecture, pre-trained and deeper NNs produce better AE-NP features, and system combination with the GMM/HMM baseline andAE-BN systems provides an additional 0.5% absolute improvement on a larger Broadcast News task.

Making Deep Belief Networks effective for large vocabulary continuous speech recognition

This paper explores the performance of DBNs in a state-of-the-art LVCSR system, showing improvements over Multi-Layer Perceptrons (MLPs) and GMM/HMMs across a variety of features on an English Broadcast News task.

Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization

A distributed neural network training algorithm, based on Hessianfree optimization, that scales to deep networks and large data sets and yields relative reductions in word error rate of 7–13% over cross-entropy training with stochastic gradient descent on two larger tasks: Switchboard and DARPA RATS noisy Levantine Arabic.

Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling

  • Brian Kingsbury
  • Computer Science
    2009 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2009
This paper demonstrates that neural-network acoustic models can be trained with sequence classification criteria using exactly the same lattice-based methods that have been developed for Gaussian mixture HMMs, and that using a sequence classification criterion in training leads to considerably better performance.

Gradient-based learning applied to document recognition

This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.