A discriminative locally weighted distance measure for speaker independent template based speech recognition

نویسندگان

  • Mike Matton
  • Mathias De Wachter
  • Dirk Van Compernolle
  • Ronald Cools
چکیده

In template based speech recognition, there is a need for a high-performant distance measure between speech frames. Some well known metrics include the Euclidean and the Mahalanobis distance. The recent tendency is to perform a local scaling of the distance metric, defining a set of classes and computing a set of weights for each of these classes. Discriminative training approaches have already proven their usefulness in various domains including speech recognition. They have the well known characteristic of training the weights for all of the classes simultaneously, and not independently of each other. In this paper, a first attempt is made to incorporate a discriminative distance measure into template based speech recognition. We use a distance measure trained by a very intuitive discriminative criterion and show that it works very well, even beating the performance results of comparable HMM-based speech recognizers.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Enhanced VQ-Based Algorithms for Speech Independent Speaker Identification

Weighted distance measure and discriminative training are two different approaches to enhance VQ-based solutions for speaker identification. To account for varying importance of the LPC coefficients in SV, the so-called partition normalized distance measure successfully used normalized feature components. This paper introduces an alternative, called heuristic weighted distance, to lift up highe...

متن کامل

Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation

A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...

متن کامل

Class-Discriminative Weighted Distortion Measure for VQ-based Speaker Identification

We consider the distortion measure in vector quantization based speaker identification system. The model of a speaker is a codebook generated from the set of feature vectors from the speakers voice sample. The matching is performed by evaluating the distortions between the unknown speech sample and the models in the speaker database. In this paper, we introduce a weighted distortion measure tha...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004