The Experts below are selected from a list of 30657 Experts worldwide ranked by ideXlab platform

Chichun Lee - One of the best experts on this subject based on the ideXlab platform.

  • adversarially enriched acoustic Code Vector learned from out of context affective corpus for robust emotion recognition
    International Conference on Acoustics Speech and Signal Processing, 2019
    Co-Authors: Chunmin Chang, Chichun Lee
    Abstract:

    Advancement in speech emotion recognition technology has brought tremendous potential in designing human-centered applications across a wide range of scenarios. However, due to the difficulty in obtaining large-scale labeled emotion corpus for every application domains, most of the existing databases are collected within disparate and limited contexts. This contextualization often undermines the variability in the emotional acoustic manifestation due to the limitation in the amount of labeled data that can be collected for each particular context. This, hence, creates a robustness issue across emotional scenarios. In this work, we propose to learn an enhanced acoustic Code Vector for in-context emotion database through adversarially learning from large out-of-context emotion corpus to obtain robust emotion recognition. We demonstrate that our framework can obtain improved recognition accuracy using low dimensional representations on two different databases, and it maintains its modeling power even when given very limited in-context training samples.

  • ICASSP - Adversarially-enriched Acoustic Code Vector Learned from Out-of-context Affective Corpus for Robust Emotion Recognition
    ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2019
    Co-Authors: Chunmin Chang, Chichun Lee
    Abstract:

    Advancement in speech emotion recognition technology has brought tremendous potential in designing human-centered applications across a wide range of scenarios. However, due to the difficulty in obtaining large-scale labeled emotion corpus for every application domains, most of the existing databases are collected within disparate and limited contexts. This contextualization often undermines the variability in the emotional acoustic manifestation due to the limitation in the amount of labeled data that can be collected for each particular context. This, hence, creates a robustness issue across emotional scenarios. In this work, we propose to learn an enhanced acoustic Code Vector for in-context emotion database through adversarially learning from large out-of-context emotion corpus to obtain robust emotion recognition. We demonstrate that our framework can obtain improved recognition accuracy using low dimensional representations on two different databases, and it maintains its modeling power even when given very limited in-context training samples.

Chunmin Chang - One of the best experts on this subject based on the ideXlab platform.

  • adversarially enriched acoustic Code Vector learned from out of context affective corpus for robust emotion recognition
    International Conference on Acoustics Speech and Signal Processing, 2019
    Co-Authors: Chunmin Chang, Chichun Lee
    Abstract:

    Advancement in speech emotion recognition technology has brought tremendous potential in designing human-centered applications across a wide range of scenarios. However, due to the difficulty in obtaining large-scale labeled emotion corpus for every application domains, most of the existing databases are collected within disparate and limited contexts. This contextualization often undermines the variability in the emotional acoustic manifestation due to the limitation in the amount of labeled data that can be collected for each particular context. This, hence, creates a robustness issue across emotional scenarios. In this work, we propose to learn an enhanced acoustic Code Vector for in-context emotion database through adversarially learning from large out-of-context emotion corpus to obtain robust emotion recognition. We demonstrate that our framework can obtain improved recognition accuracy using low dimensional representations on two different databases, and it maintains its modeling power even when given very limited in-context training samples.

  • ICASSP - Adversarially-enriched Acoustic Code Vector Learned from Out-of-context Affective Corpus for Robust Emotion Recognition
    ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2019
    Co-Authors: Chunmin Chang, Chichun Lee
    Abstract:

    Advancement in speech emotion recognition technology has brought tremendous potential in designing human-centered applications across a wide range of scenarios. However, due to the difficulty in obtaining large-scale labeled emotion corpus for every application domains, most of the existing databases are collected within disparate and limited contexts. This contextualization often undermines the variability in the emotional acoustic manifestation due to the limitation in the amount of labeled data that can be collected for each particular context. This, hence, creates a robustness issue across emotional scenarios. In this work, we propose to learn an enhanced acoustic Code Vector for in-context emotion database through adversarially learning from large out-of-context emotion corpus to obtain robust emotion recognition. We demonstrate that our framework can obtain improved recognition accuracy using low dimensional representations on two different databases, and it maintains its modeling power even when given very limited in-context training samples.

Wai-yip Chan - One of the best experts on this subject based on the ideXlab platform.

  • generalized product Code Vector quantization a family of efficient techniques for signal compression
    Digital Signal Processing, 1994
    Co-Authors: Wai-yip Chan, Allen Gersho
    Abstract:

    Abstract Under the constraint of limited complexity, structured Vector quantization (VQ) can outperform unstructured VQ. We show that a large family of structured VQ schemes are special cases of a generalized product Code (GPC) model. In this model, an input Vector is (a) decomposed by the enCoder into multiple feature Vectors that are sequentially enCoded, where the choice of Codebook for a particular feature depends on how the prior feature was enCoded, and (b) reproduced by the deCoder from a synthesis operation on the quantized feature Vectors. Many existing VQ structures and audio and visual signal compression schemes can be advantageously studied, extended, and designed from the perspective of this model. We present design methods for GPCs, including: (i) algorithms that allow a controlled trade-off between reproduction fidelity (or distortion) and encoding or storage complexity; (ii) an algorithm paradigm for joint optimization of multiple Codebooks. The GPC methods are illustrated with applications to summation product Codes, which include the now-classical schemes of multistage VQ (MSVQ) and tree-structured VQ (TSVQ). Among the results is a procedure for designing balanced TSVQ Codebooks to arbitrary depths, and MSVQ-TSVQ hybrid structures that furnish enhanced trade-offs between complexity and distortion-rate performance.

  • ICASSP - The design of generalized product-Code Vector quantizers
    [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics Speech and Signal Processing, 1992
    Co-Authors: Wai-yip Chan
    Abstract:

    Structured Vector quantization (VQ) can achieve superior performance-complexity tradeoffs in comparison with unstructured VQ. Many VQ schemes fall into a class of structured VQ called product Codes. A generalization of product Codes wherein a feature may have multiple Codebooks is considered. For the design of generalized product Codes (GPCs) methodologies are devised for achieving independent tradeoffs of Codebook storage complexity and encoding complexity versus distortion performance and for the joint optimization of feature Codebooks. This GPC design framework makes it possible to attain many intermediate levels of rate-distortion performance between unstructured VQ and conventional product Codes. Thus, the performance of unstructured VQ may be approached with a lower-complexity GPC. The framework is illustrated using numerical results from the quantization of speech line-spectral frequency parameters. >

Yann L Cun - One of the best experts on this subject based on the ideXlab platform.

  • efficient learning of sparse representations with an energy based model
    Neural Information Processing Systems, 2006
    Co-Authors: Marcaurelio Ranzato, Christopher S Poultney, Sumit Chopra, Yann L Cun
    Abstract:

    We describe a novel unsupervised method for learning sparse, overcomplete features. The model uses a linear enCoder, and a linear deCoder preceded by a sparsifying non-linearity that turns a Code Vector into a quasi-binary sparse Code Vector. Given an input, the optimal Code minimizes the distance between the output of the deCoder and the input patch while being as similar as possible to the enCoder output. Learning proceeds in a two-phase EM-like fashion: (1) compute the minimum-energy Code Vector, (2) adjust the parameters of the enCoder and deCoder so as to decrease the energy. The model produces "stroke detectors" when trained on handwritten numerals, and Gabor-like filters when trained on natural image patches. Inference and learning are very fast, requiring no preprocessing, and no expensive sampling. Using the proposed unsupervised method to initialize the first layer of a convolutional network, we achieved an error rate slightly lower than the best reported result on the MNIST dataset. Finally, an extension of the method is described to learn topographical filter maps.

S. P. Luttrell - One of the best experts on this subject based on the ideXlab platform.

  • Code Vector density in topographic mappings: Scalar case
    IEEE transactions on neural networks, 1991
    Co-Authors: S. P. Luttrell
    Abstract:

    The author derives some new results that build on his earlier work (1989) of combining Vector quantization (VQ) theory and topographic mapping (TM) theory. A VQ model (with a noisy transmission medium) is used to model the processes that occur in TMs, which leads to the standard TM training algorithm, albeit with a slight modification to the encoding process. To emphasize this difference, the model is called a topographic Vector quantizer (TVQ). In the continuum limit of the one-dimensional (scalar) TVQ. It is found that the density of Code Vectors is proportional to P(x)/sup a/ ( alpha =1/3) assuming that the transmission medium introduces additive noise with a zero-mean, symmetric, monotically decreasing probability density. This result is dramatically different from the result that is predicted when the standard TM training algorithm is used with a uniform symmetric neighborhood (-n, +n), and it is noted that this difference arises entirely from using minimum distortion rather than nearest neighbor encoding. >