The Experts below are selected from a list of 83433 Experts worldwide ranked by ideXlab platform

Markus Puschel - One of the best experts on this subject based on the ideXlab platform.

  • computer generation of general size Linear Transform libraries
    Symposium on Code Generation and Optimization, 2009
    Co-Authors: Yevgen Voronenko, Frederic De Mesmay, Markus Puschel
    Abstract:

    The development of high-performance libraries has become extraordinarily difficult due to multiple processor cores, vector instruction sets, and deep memory hierarchies. Often, the library has to be reimplemented and reoptimized, when a new platform is released. In this paper we show how to automatically generate general input-size libraries for the domain of Linear Transforms. The input to our generator is a formal specification of the Transform and the recursive algorithms the library should use; the output is a library that supports general input size, is vectorized and multithreaded, provides an adaptation mechanism for the memory hierarchy, and has excellent performance, comparable to or better than the best human-written libraries. Further, we show that our library generator enables various customizations; one example is the generation of Java libraries.

  • CGO - Computer Generation of General Size Linear Transform Libraries
    2009 International Symposium on Code Generation and Optimization, 2009
    Co-Authors: Yevgen Voronenko, Frederic De Mesmay, Markus Puschel
    Abstract:

    The development of high-performance libraries has become extraordinarily difficult due to multiple processor cores, vector instruction sets, and deep memory hierarchies. Often, the library has to be reimplemented and reoptimized, when a new platform is released. In this paper we show how to automatically generate general input-size libraries for the domain of Linear Transforms. The input to our generator is a formal specification of the Transform and the recursive algorithms the library should use; the output is a library that supports general input size, is vectorized and multithreaded, provides an adaptation mechanism for the memory hierarchy, and has excellent performance, comparable to or better than the best human-written libraries. Further, we show that our library generator enables various customizations; one example is the generation of Java libraries.

Yevgen Voronenko - One of the best experts on this subject based on the ideXlab platform.

  • computer generation of general size Linear Transform libraries
    Symposium on Code Generation and Optimization, 2009
    Co-Authors: Yevgen Voronenko, Frederic De Mesmay, Markus Puschel
    Abstract:

    The development of high-performance libraries has become extraordinarily difficult due to multiple processor cores, vector instruction sets, and deep memory hierarchies. Often, the library has to be reimplemented and reoptimized, when a new platform is released. In this paper we show how to automatically generate general input-size libraries for the domain of Linear Transforms. The input to our generator is a formal specification of the Transform and the recursive algorithms the library should use; the output is a library that supports general input size, is vectorized and multithreaded, provides an adaptation mechanism for the memory hierarchy, and has excellent performance, comparable to or better than the best human-written libraries. Further, we show that our library generator enables various customizations; one example is the generation of Java libraries.

  • CGO - Computer Generation of General Size Linear Transform Libraries
    2009 International Symposium on Code Generation and Optimization, 2009
    Co-Authors: Yevgen Voronenko, Frederic De Mesmay, Markus Puschel
    Abstract:

    The development of high-performance libraries has become extraordinarily difficult due to multiple processor cores, vector instruction sets, and deep memory hierarchies. Often, the library has to be reimplemented and reoptimized, when a new platform is released. In this paper we show how to automatically generate general input-size libraries for the domain of Linear Transforms. The input to our generator is a formal specification of the Transform and the recursive algorithms the library should use; the output is a library that supports general input size, is vectorized and multithreaded, provides an adaptation mechanism for the memory hierarchy, and has excellent performance, comparable to or better than the best human-written libraries. Further, we show that our library generator enables various customizations; one example is the generation of Java libraries.

Philip C. Woodland - One of the best experts on this subject based on the ideXlab platform.

  • Discriminative Linear Transforms for speaker adaptation
    2001
    Co-Authors: Lf Uebel, Philip C. Woodland
    Abstract:

    Linear Transform adaptation techniques such as Maximum Likelihood Linear Regression (MLLR) are a popular and effective family of methods for speaker adaptation. MLLR estimates Transform parameters for Gaussian means and variances using a maximum likelihood (ML) objective function. This paper discusses the use of an alternative discriminative objective function for Linear Transform estimation, which is an interpolation of the maximum mutual information (MMI) objective function and the ML criterion. This Discriminative Linear Transform (DLT) more directly reduces the word error rate of the adaptation data than MLLR and assuming good generalisation will also reduce test-set error rates. The implementation of DLT estimation is discussed and test-data recognition results compared to those from standard unconstrained MLLR (mean and variance adaptation) using the 1994 WSJ/NAB spoke 3 non-native adaptation task. The results show that relative reductions in word error rate between 7% and 19% can be obtained by using DLTs.

  • ICASSP - Improvements in Linear Transform based speaker adaptation
    2001 IEEE International Conference on Acoustics Speech and Signal Processing. Proceedings (Cat. No.01CH37221), 1
    Co-Authors: Lf Uebel, Philip C. Woodland
    Abstract:

    Presents three forms of Linear Transform based speaker adaptation that can give better performance than standard maximum likelihood Linear regression (MLLR) adaptation. For unsupervised adaptation, a lattice-based technique is introduced which is compared to MLLR using confidence scores. For supervised adaptation, estimation of the adaptation matrices using the maximum mutual information criterion is discussed which leads to the MMILR approach. Recognition experiments show that lattice MLLR can reduce word error rates on a Switchboard task by 1.4% absolute. For recognition of non-native speech from the Wall Street Journal database, a reduction in word error rate of 10-16% relative was obtained using MMILR compared to standard MLLR.

  • ICASSP (1) - MPE-based discriminative Linear Transform for speaker adaptation
    2004 IEEE International Conference on Acoustics Speech and Signal Processing, 1
    Co-Authors: L. Wang, Philip C. Woodland
    Abstract:

    We present a discriminative method for speaker adaptation, where the minimum phone error (MPE) criterion is used to estimate the discriminative Linear Transforms (DLTs), including both mean and diagonal variance Transforms. The I-smoothing technique is essential to improve the generalization of DLTs. Experiments on supervised adaptation for non-native speakers on the North American Business (NAB) Spoke 3 task show that MPE-based DLT outperforms both MLLR and a previously proposed discriminative method for Transform estimation. Preliminary experiments on unsupervised DLT estimation are also reported for conversational telephone speech transcription.

Wen Gao - One of the best experts on this subject based on the ideXlab platform.

  • Linear Transform based motion compensated prediction for luminance intensity changes
    International Symposium on Circuits and Systems, 2005
    Co-Authors: Debing Liu, Qingming Huang, Wen Gao
    Abstract:

    A Linear Transform based motion compensated prediction (LT-MCP) scheme is proposed in this paper to improve the efficiency of inter-frame prediction when the intensity of luminance changes abruptly across frames. Either uniform or non-uniform intensity changes can be well processed as the proposed scheme is applied at macroblock (MB) level. LT-MCP is implemented based on the H.264 reference software to evaluate its performance. For those sequences with significant luminance changes across frames, such as Crew, we can achieve about 1.5dB improvement over the conventional MCP with intra prediction disabled and about 0.8dB gain with intra prediction enabled. For those sequences without obvious luminance changes, the proposed scheme also works better.

  • ISCAS (1) - Linear Transform based motion compensated prediction for luminance intensity changes
    2005 IEEE International Symposium on Circuits and Systems, 1
    Co-Authors: Debing Liu, Qingming Huang, Wen Gao
    Abstract:

    A Linear Transform based motion compensated prediction (LT-MCP) scheme is proposed in this paper to improve the efficiency of inter-frame prediction when the intensity of luminance changes abruptly across frames. Either uniform or non-uniform intensity changes can be well processed as the proposed scheme is applied at macroblock (MB) level. LT-MCP is implemented based on the H.264 reference software to evaluate its performance. For those sequences with significant luminance changes across frames, such as Crew, we can achieve about 1.5dB improvement over the conventional MCP with intra prediction disabled and about 0.8dB gain with intra prediction enabled. For those sequences without obvious luminance changes, the proposed scheme also works better.

Frederic De Mesmay - One of the best experts on this subject based on the ideXlab platform.

  • computer generation of general size Linear Transform libraries
    Symposium on Code Generation and Optimization, 2009
    Co-Authors: Yevgen Voronenko, Frederic De Mesmay, Markus Puschel
    Abstract:

    The development of high-performance libraries has become extraordinarily difficult due to multiple processor cores, vector instruction sets, and deep memory hierarchies. Often, the library has to be reimplemented and reoptimized, when a new platform is released. In this paper we show how to automatically generate general input-size libraries for the domain of Linear Transforms. The input to our generator is a formal specification of the Transform and the recursive algorithms the library should use; the output is a library that supports general input size, is vectorized and multithreaded, provides an adaptation mechanism for the memory hierarchy, and has excellent performance, comparable to or better than the best human-written libraries. Further, we show that our library generator enables various customizations; one example is the generation of Java libraries.

  • CGO - Computer Generation of General Size Linear Transform Libraries
    2009 International Symposium on Code Generation and Optimization, 2009
    Co-Authors: Yevgen Voronenko, Frederic De Mesmay, Markus Puschel
    Abstract:

    The development of high-performance libraries has become extraordinarily difficult due to multiple processor cores, vector instruction sets, and deep memory hierarchies. Often, the library has to be reimplemented and reoptimized, when a new platform is released. In this paper we show how to automatically generate general input-size libraries for the domain of Linear Transforms. The input to our generator is a formal specification of the Transform and the recursive algorithms the library should use; the output is a library that supports general input size, is vectorized and multithreaded, provides an adaptation mechanism for the memory hierarchy, and has excellent performance, comparable to or better than the best human-written libraries. Further, we show that our library generator enables various customizations; one example is the generation of Java libraries.