The Experts below are selected from a list of 2712 Experts worldwide ranked by ideXlab platform

Narayan Biswal - One of the best experts on this subject based on the ideXlab platform.

  • ICASSP - Sufficiency Quantification for Seamless Text-Independent Speaker Enrollment
    2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018
    Co-Authors: Gokcen Cilingir, Jonathan Huang, Mandar S Joshi, Narayan Biswal
    Abstract:

    Text-independent speaker recognition (TI-SR) requires a lengthy Enrollment Process that involves asking dedicated time from the user to create a reliable model of their voice. Seamless Enrollment is a highly attractive feature which refers to the Enrollment Process that happens in the background and asks for no dedicated time from the user. One of the key problems in a fully automated seamless Enrollment Process is to determine the sufficiency of a given utterance collection for the purpose of TI-SR. No known metric exists in the literature to quantify sufficiency. This paper introduces a novel metric called phoneme-richness score. Quality of a sufficiency metric can be assessed via its correlation with the TI-SR performance. Our assessment shows that phoneme-richness score achieves −0.96 correlation with TI-SR performance (measured in equal error rate), which is highly significant, whereas a naive sufficiency metric like speech duration achieves only −0.68 correlation.

  • Sufficiency Quantification for Seamless Text-Independent Speaker Enrollment
    2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018
    Co-Authors: Gokcen Cilingir, Jonathan Huang, Mandar S Joshi, Narayan Biswal
    Abstract:

    Text-independent speaker recognition (TI-SR) requires a lengthy Enrollment Process that involves asking dedicated time from the user to create a reliable model of their voice. Seamless Enrollment is a highly attractive feature which refers to the Enrollment Process that happens in the background and asks for no dedicated time from the user. One of the key problems in a fully automated seamless Enrollment Process is to determine the sufficiency of a given utterance collection for the purpose of TI-SR. No known metric exists in the literature to quantify sufficiency. This paper introduces a novel metric called phoneme-richness score. Quality of a sufficiency metric can be assessed via its correlation with the TI-SR performance. Our assessment shows that phoneme-richness score achieves -0.96 correlation with TI-SR performance (measured in equal error rate), which is highly significant, whereas a naive sufficiency metric like speech duration achieves only -0.68 correlation.

Gokcen Cilingir - One of the best experts on this subject based on the ideXlab platform.

  • ICASSP - Sufficiency Quantification for Seamless Text-Independent Speaker Enrollment
    2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018
    Co-Authors: Gokcen Cilingir, Jonathan Huang, Mandar S Joshi, Narayan Biswal
    Abstract:

    Text-independent speaker recognition (TI-SR) requires a lengthy Enrollment Process that involves asking dedicated time from the user to create a reliable model of their voice. Seamless Enrollment is a highly attractive feature which refers to the Enrollment Process that happens in the background and asks for no dedicated time from the user. One of the key problems in a fully automated seamless Enrollment Process is to determine the sufficiency of a given utterance collection for the purpose of TI-SR. No known metric exists in the literature to quantify sufficiency. This paper introduces a novel metric called phoneme-richness score. Quality of a sufficiency metric can be assessed via its correlation with the TI-SR performance. Our assessment shows that phoneme-richness score achieves −0.96 correlation with TI-SR performance (measured in equal error rate), which is highly significant, whereas a naive sufficiency metric like speech duration achieves only −0.68 correlation.

  • Sufficiency Quantification for Seamless Text-Independent Speaker Enrollment
    2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018
    Co-Authors: Gokcen Cilingir, Jonathan Huang, Mandar S Joshi, Narayan Biswal
    Abstract:

    Text-independent speaker recognition (TI-SR) requires a lengthy Enrollment Process that involves asking dedicated time from the user to create a reliable model of their voice. Seamless Enrollment is a highly attractive feature which refers to the Enrollment Process that happens in the background and asks for no dedicated time from the user. One of the key problems in a fully automated seamless Enrollment Process is to determine the sufficiency of a given utterance collection for the purpose of TI-SR. No known metric exists in the literature to quantify sufficiency. This paper introduces a novel metric called phoneme-richness score. Quality of a sufficiency metric can be assessed via its correlation with the TI-SR performance. Our assessment shows that phoneme-richness score achieves -0.96 correlation with TI-SR performance (measured in equal error rate), which is highly significant, whereas a naive sufficiency metric like speech duration achieves only -0.68 correlation.

Gregory Stiber - One of the best experts on this subject based on the ideXlab platform.

  • characterizing the decision Process leading to Enrollment in master s programs further application of the Enrollment Process model
    Journal of Marketing for Higher Education, 2001
    Co-Authors: Gregory Stiber
    Abstract:

    ABSTRACT As part of an ongoing market research function, the administration at a private university's business school implemented a project to better understand the composition of its master's students. This research was an extension of a similar study conducted for the school's doctoral programs. Like the earlier study on doctoral students, a behavioral approach that employed a theoretical model of the decision Process leading to Enrollment was applied to master's students. This Enrollment Process model was utilized to guide the implementation of a survey that sampled the school's current students. Application of this model to questionnaire development procedures is also presented. Based on the information collected, the decision Process leading to Enrollment in the master's business programs was characterized. Quadrant analysis was applied to selected data derived from the Enrollment Process model in order to develop a two dimensional profile of students. In practice, this depiction provided insight to ...

  • characterizing the decision Process leading to Enrollment in doctoral programs theory application and practice
    Journal of Marketing for Higher Education, 2000
    Co-Authors: Gregory Stiber
    Abstract:

    As a result of environmental changes, the administration at a private university's business school determined that there was a need to better understand the market for doctoral education. A behavioral approach was employed to study this market. A theoretical model of the decision Process leading to Enrollment in the school's doctoral business program was developed. This Enrollment Process model was utilized to guide the implementation of a survey that sampled the school's current students. Application of this model to questionnaire development procedures is also presented. Based on the information collected, the decision Process leading to Enrollment in the doctoral business program was characterized. In practice, this depiction provided insight to student behavior and the substance of the school's current market. The usefulness and applicability of the Enrollment Process model in achieving Enrollment management objectives is also discussed.

Jonathan Huang - One of the best experts on this subject based on the ideXlab platform.

  • ICASSP - Sufficiency Quantification for Seamless Text-Independent Speaker Enrollment
    2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018
    Co-Authors: Gokcen Cilingir, Jonathan Huang, Mandar S Joshi, Narayan Biswal
    Abstract:

    Text-independent speaker recognition (TI-SR) requires a lengthy Enrollment Process that involves asking dedicated time from the user to create a reliable model of their voice. Seamless Enrollment is a highly attractive feature which refers to the Enrollment Process that happens in the background and asks for no dedicated time from the user. One of the key problems in a fully automated seamless Enrollment Process is to determine the sufficiency of a given utterance collection for the purpose of TI-SR. No known metric exists in the literature to quantify sufficiency. This paper introduces a novel metric called phoneme-richness score. Quality of a sufficiency metric can be assessed via its correlation with the TI-SR performance. Our assessment shows that phoneme-richness score achieves −0.96 correlation with TI-SR performance (measured in equal error rate), which is highly significant, whereas a naive sufficiency metric like speech duration achieves only −0.68 correlation.

  • Sufficiency Quantification for Seamless Text-Independent Speaker Enrollment
    2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018
    Co-Authors: Gokcen Cilingir, Jonathan Huang, Mandar S Joshi, Narayan Biswal
    Abstract:

    Text-independent speaker recognition (TI-SR) requires a lengthy Enrollment Process that involves asking dedicated time from the user to create a reliable model of their voice. Seamless Enrollment is a highly attractive feature which refers to the Enrollment Process that happens in the background and asks for no dedicated time from the user. One of the key problems in a fully automated seamless Enrollment Process is to determine the sufficiency of a given utterance collection for the purpose of TI-SR. No known metric exists in the literature to quantify sufficiency. This paper introduces a novel metric called phoneme-richness score. Quality of a sufficiency metric can be assessed via its correlation with the TI-SR performance. Our assessment shows that phoneme-richness score achieves -0.96 correlation with TI-SR performance (measured in equal error rate), which is highly significant, whereas a naive sufficiency metric like speech duration achieves only -0.68 correlation.

Mandar S Joshi - One of the best experts on this subject based on the ideXlab platform.

  • ICASSP - Sufficiency Quantification for Seamless Text-Independent Speaker Enrollment
    2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018
    Co-Authors: Gokcen Cilingir, Jonathan Huang, Mandar S Joshi, Narayan Biswal
    Abstract:

    Text-independent speaker recognition (TI-SR) requires a lengthy Enrollment Process that involves asking dedicated time from the user to create a reliable model of their voice. Seamless Enrollment is a highly attractive feature which refers to the Enrollment Process that happens in the background and asks for no dedicated time from the user. One of the key problems in a fully automated seamless Enrollment Process is to determine the sufficiency of a given utterance collection for the purpose of TI-SR. No known metric exists in the literature to quantify sufficiency. This paper introduces a novel metric called phoneme-richness score. Quality of a sufficiency metric can be assessed via its correlation with the TI-SR performance. Our assessment shows that phoneme-richness score achieves −0.96 correlation with TI-SR performance (measured in equal error rate), which is highly significant, whereas a naive sufficiency metric like speech duration achieves only −0.68 correlation.

  • Sufficiency Quantification for Seamless Text-Independent Speaker Enrollment
    2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018
    Co-Authors: Gokcen Cilingir, Jonathan Huang, Mandar S Joshi, Narayan Biswal
    Abstract:

    Text-independent speaker recognition (TI-SR) requires a lengthy Enrollment Process that involves asking dedicated time from the user to create a reliable model of their voice. Seamless Enrollment is a highly attractive feature which refers to the Enrollment Process that happens in the background and asks for no dedicated time from the user. One of the key problems in a fully automated seamless Enrollment Process is to determine the sufficiency of a given utterance collection for the purpose of TI-SR. No known metric exists in the literature to quantify sufficiency. This paper introduces a novel metric called phoneme-richness score. Quality of a sufficiency metric can be assessed via its correlation with the TI-SR performance. Our assessment shows that phoneme-richness score achieves -0.96 correlation with TI-SR performance (measured in equal error rate), which is highly significant, whereas a naive sufficiency metric like speech duration achieves only -0.68 correlation.