Genetically optimised feedforward neural networks for speaker identification

نویسندگان

  • Richard C. Price
  • Jonathan P. Willmore
  • William J. J. Roberts
  • Kathleen Zyga
چکیده

The problem of establishing the identity of a speaker from a given utterance has been conventionally addressed using techniques such as Gaussian Mixture Models (GMM's) that model the characteristics of a known speaker via means and covariances. In this paper we pose the task as a binary classification problem, and whilst in principle any one of a number of classifiers could be applied, this work compares the performance of genetically optimised neural networks versus the conventional approach of GMM’s. The test data used in the experiments was the data used for the 1996 National Institute for Standards Technology (NIST) evaluation of speaker identification systems. APPROVED FOR PUBLIC RELEASE

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

DEPARTMENT OF DEFENCE DEFENCE SCIENCE & TECHNOLOGY ORGANISATION DSTO Genetically Optimised Feedforward Neural Networks for Speaker Identification

The problem of establishing the identity of a speaker from a given utterance has been conventionally addressed using techniques such as Gaussian Mixture Models (GMMs) that model the characteristics of a known speaker via means and covariances. In this paper we pose the task as a binary classification problem, and whilst in principle any one of a number of classifiers could be applied, this work...

متن کامل

Optimised Training Techniques for Feedforward Neural Networks

................................................................................................................................................................. 1

متن کامل

Speaker recognition with recurrent neural networks

We report on the application of recurrent neural nets in a openset text-dependent speaker identification task. The motivation for applying recurrent neural nets to this domain is to find out if their ability to take short-term spectral features but yet respond to long-term temporal events is advantageous for speaker identification. We use a feedforward net architecture adapted from that introdu...

متن کامل

بررسی کارایی روش‌های مختلف هوش مصنوعی و روش آماری در برآورد میزان رواناب (مطالعه موردی: حوزه شهید نوری کاخک گناباد)

Rainfall-runoff models are used in the field of hydrology and runoff estimation for many years, but despite existing numerous models, the regular release of new models shows that there is still not a model that can provide sophisticated estimations with high accuracy and performance. In order to achieve the best results, modeling and identification of factors affecting the output of the model i...

متن کامل

Deep Speaker Embeddings for Short-Duration Speaker Verification

The performance of a state-of-the-art speaker verification system is severely degraded when it is presented with trial recordings of short duration. In this work we propose to use deep neural networks to learn short-duration speaker embeddings. We focus on the 5s-5s condition, wherein both sides of a verification trial are 5 seconds long. In our previous work we established that learning a non-...

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 2000