The Experts below are selected from a list of 62529 Experts worldwide ranked by ideXlab platform

François Yvon - One of the best experts on this subject based on the ideXlab platform.

  • structured output Layer Neural Network language models for speech recognition
    IEEE Transactions on Audio Speech and Language Processing, 2013
    Co-Authors: Ilya Oparin, Alexandre Allauzen, Jean-luc Gauvain, François Yvon
    Abstract:

    This paper extends a novel Neural Network language model (NNLM) which relies on word clustering to structure the output vocabulary: Structured OUtput Layer (SOUL) NNLM. This model is able to handle arbitrarily-sized vocabularies, hence dispensing with the need for shortlists that are commonly used in NNLMs. Several softmax Layers replace the standard output Layer in this model. The output structure depends on the word clustering which is based on the continuous word representation determined by the NNLM. Mandarin and Arabic data are used to evaluate the SOUL NNLM accuracy via speech-to-text experiments. Well tuned speech-to-text systems (with error rates around 10%) serve as the baselines. The SOUL model achieves consistent improvements over a classical shortlist NNLM both in terms of perplexity and recognition accuracy for these two languages that are quite different in terms of their internal structure and recognition vocabulary size. An enhanced training scheme is proposed that allows more data to be used at each training iteration of the Neural Network.

  • Structured output Layer Neural Network language model
    ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2011
    Co-Authors: Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-luc Gauvain, François Yvon
    Abstract:

    This paper introduces a new Neural Network language model (NNLM) based on word clustering to structure the output vo-cabulary: Structured Output Layer NNLM. This model is able to handle vocabularies of arbitrary size, hence dispensing with the design of short-lists that are commonly used in NNLMs. Several softmax Layers replace the standard output Layer in this model. The output structure depends on the word cluster-ing which uses the continuous word representation induced by a NNLM. The GALE Mandarin data was used to carry out the speech-to-text experiments and evaluate the NNLMs. On this data the well tuned baseline system has a character er-ror rate under 10%. Our model achieves consistent improve-ments over the combination of an n-gram model and classical short-list NNLMs both in terms of perplexity and recognition accuracy.

Ilya Oparin - One of the best experts on this subject based on the ideXlab platform.

  • structured output Layer Neural Network language models for speech recognition
    IEEE Transactions on Audio Speech and Language Processing, 2013
    Co-Authors: Ilya Oparin, Alexandre Allauzen, Jean-luc Gauvain, François Yvon
    Abstract:

    This paper extends a novel Neural Network language model (NNLM) which relies on word clustering to structure the output vocabulary: Structured OUtput Layer (SOUL) NNLM. This model is able to handle arbitrarily-sized vocabularies, hence dispensing with the need for shortlists that are commonly used in NNLMs. Several softmax Layers replace the standard output Layer in this model. The output structure depends on the word clustering which is based on the continuous word representation determined by the NNLM. Mandarin and Arabic data are used to evaluate the SOUL NNLM accuracy via speech-to-text experiments. Well tuned speech-to-text systems (with error rates around 10%) serve as the baselines. The SOUL model achieves consistent improvements over a classical shortlist NNLM both in terms of perplexity and recognition accuracy for these two languages that are quite different in terms of their internal structure and recognition vocabulary size. An enhanced training scheme is proposed that allows more data to be used at each training iteration of the Neural Network.

  • Structured output Layer Neural Network language model
    ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2011
    Co-Authors: Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-luc Gauvain, François Yvon
    Abstract:

    This paper introduces a new Neural Network language model (NNLM) based on word clustering to structure the output vo-cabulary: Structured Output Layer NNLM. This model is able to handle vocabularies of arbitrary size, hence dispensing with the design of short-lists that are commonly used in NNLMs. Several softmax Layers replace the standard output Layer in this model. The output structure depends on the word cluster-ing which uses the continuous word representation induced by a NNLM. The GALE Mandarin data was used to carry out the speech-to-text experiments and evaluate the NNLMs. On this data the well tuned baseline system has a character er-ror rate under 10%. Our model achieves consistent improve-ments over the combination of an n-gram model and classical short-list NNLMs both in terms of perplexity and recognition accuracy.

Alexandre Allauzen - One of the best experts on this subject based on the ideXlab platform.

  • structured output Layer Neural Network language models for speech recognition
    IEEE Transactions on Audio Speech and Language Processing, 2013
    Co-Authors: Ilya Oparin, Alexandre Allauzen, Jean-luc Gauvain, François Yvon
    Abstract:

    This paper extends a novel Neural Network language model (NNLM) which relies on word clustering to structure the output vocabulary: Structured OUtput Layer (SOUL) NNLM. This model is able to handle arbitrarily-sized vocabularies, hence dispensing with the need for shortlists that are commonly used in NNLMs. Several softmax Layers replace the standard output Layer in this model. The output structure depends on the word clustering which is based on the continuous word representation determined by the NNLM. Mandarin and Arabic data are used to evaluate the SOUL NNLM accuracy via speech-to-text experiments. Well tuned speech-to-text systems (with error rates around 10%) serve as the baselines. The SOUL model achieves consistent improvements over a classical shortlist NNLM both in terms of perplexity and recognition accuracy for these two languages that are quite different in terms of their internal structure and recognition vocabulary size. An enhanced training scheme is proposed that allows more data to be used at each training iteration of the Neural Network.

  • Structured output Layer Neural Network language model
    ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2011
    Co-Authors: Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-luc Gauvain, François Yvon
    Abstract:

    This paper introduces a new Neural Network language model (NNLM) based on word clustering to structure the output vo-cabulary: Structured Output Layer NNLM. This model is able to handle vocabularies of arbitrary size, hence dispensing with the design of short-lists that are commonly used in NNLMs. Several softmax Layers replace the standard output Layer in this model. The output structure depends on the word cluster-ing which uses the continuous word representation induced by a NNLM. The GALE Mandarin data was used to carry out the speech-to-text experiments and evaluate the NNLMs. On this data the well tuned baseline system has a character er-ror rate under 10%. Our model achieves consistent improve-ments over the combination of an n-gram model and classical short-list NNLMs both in terms of perplexity and recognition accuracy.

Jean-luc Gauvain - One of the best experts on this subject based on the ideXlab platform.

  • structured output Layer Neural Network language models for speech recognition
    IEEE Transactions on Audio Speech and Language Processing, 2013
    Co-Authors: Ilya Oparin, Alexandre Allauzen, Jean-luc Gauvain, François Yvon
    Abstract:

    This paper extends a novel Neural Network language model (NNLM) which relies on word clustering to structure the output vocabulary: Structured OUtput Layer (SOUL) NNLM. This model is able to handle arbitrarily-sized vocabularies, hence dispensing with the need for shortlists that are commonly used in NNLMs. Several softmax Layers replace the standard output Layer in this model. The output structure depends on the word clustering which is based on the continuous word representation determined by the NNLM. Mandarin and Arabic data are used to evaluate the SOUL NNLM accuracy via speech-to-text experiments. Well tuned speech-to-text systems (with error rates around 10%) serve as the baselines. The SOUL model achieves consistent improvements over a classical shortlist NNLM both in terms of perplexity and recognition accuracy for these two languages that are quite different in terms of their internal structure and recognition vocabulary size. An enhanced training scheme is proposed that allows more data to be used at each training iteration of the Neural Network.

  • Structured output Layer Neural Network language model
    ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2011
    Co-Authors: Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-luc Gauvain, François Yvon
    Abstract:

    This paper introduces a new Neural Network language model (NNLM) based on word clustering to structure the output vo-cabulary: Structured Output Layer NNLM. This model is able to handle vocabularies of arbitrary size, hence dispensing with the design of short-lists that are commonly used in NNLMs. Several softmax Layers replace the standard output Layer in this model. The output structure depends on the word cluster-ing which uses the continuous word representation induced by a NNLM. The GALE Mandarin data was used to carry out the speech-to-text experiments and evaluate the NNLMs. On this data the well tuned baseline system has a character er-ror rate under 10%. Our model achieves consistent improve-ments over the combination of an n-gram model and classical short-list NNLMs both in terms of perplexity and recognition accuracy.

Huseyin H Sayan - One of the best experts on this subject based on the ideXlab platform.

  • a neuro fuzzy controller for speed control of a permanent magnet synchronous motor drive
    Expert Systems With Applications, 2008
    Co-Authors: Cetin Elmas, Oguz Ustun, Huseyin H Sayan
    Abstract:

    This paper introduces a neuro-fuzzy controller (NFC) for the speed control of a PMSM. A four Layer Neural Network (NN) is used to adjust input and output parameters of membership functions in a fuzzy logic controller (FLC). The back propagation learning algorithm is used for training this Network. The performance of the proposed controller is verified by both simulations and experiments. The hardware implementation of the controllers is made using a TMS320F240 DSP. The results are compared with the results obtain from a Proportional+Integral (PI) controller. Simulation and experimental results indicate that the proposed NFC is reliable and effective for the speed control of the PMSM over a wide range of operations of the PMSM drive.