Histogram Equalization Based Front-end Processing for Noisy Speech Recognition

نویسندگان

  • IBRAHIM MISSAOUI
  • ZIED LACHIRI
چکیده

In this paper, we present Gabor features extraction based on front-end processing using histogram equalization for noisy speech recognition. The proposed features named as Histogram Equalization of Gabor Bark Spectrum features, HeqGBS features are extracted using 2-D Gabor processing followed by a histogram equalization step from spectro-temporal representation of Bark spectrum of speech signal. The histogram equalization is used as front-end processing in order to reduce and eliminate the undesired information from the used spectrum representation. The proposed HeqGBS features are evaluated on recognition task of noisy isolated speech words using HMM. The obtained recognition rates confirm that the HeqGBS features yield interesting results compared to those of the Gabor features which are obtained from log Mel-spectrogram.

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

A new feature extraction front-end for robust speech recognition using progressive histogram equalization and multi-eigenvector temporal filtering

In this paper, a new feature extraction front-end for robust speech recognition using progressive histogram equalization and multi-eigenvector temporal filtering is proposed. The progressive histogram equalization (PHEQ) performs the histogram equalization (HEQ) progressively with respect to a reference interval which moves with the present frame to be processed. The multi-eigenvector temporal ...

متن کامل

Front-End Compensation Methods for LVCSR Under Lombard Effect

This study analyzes the impact of noisy background variations and Lombard effect (LE) on large vocabulary continuous speech recognition (LVCSR). Robustness of several front-end feature extraction strategies combined with state-of-the-art feature distribution normalizations is tested on neutral and Lombard speech from the UT-Scope database presented in two types of background noise at various le...

متن کامل

Feature Compensation Combining SNR - Dependent Feature Reconstruction and Class Histogram Equalization

Youngjoo Suh et al. 753 ABSTRACT⎯In this letter, we propose a new histogram equalization technique for feature compensation in speech recognition under noisy environments. The proposed approach combines a signal-to-noise-ratio–dependent feature reconstruction method and the class histogram equalization technique to effectively reduce the acoustic mismatch present in noisy speech features. Exper...

متن کامل

The Use of Dictionary Learning Approach for Robustness Speech Recognition

The performance of automatic speech recognition (ASR) often degrades dramatically in noisy environments. In this paper, we present a novel use of dictionary learning approach to normalizing the magnitude modulation spectra of speech features so as to retain more noise-resistant and important acoustic characteristics. To this end, we employ the K-SVD method to create sparse representations for a...

متن کامل

Histogram Equalization to Model Adaptation for Robust Speech Recognition

We propose a new model adaptation method based on the histogram equalization technique for providing robustness in noisy environments. The trained acoustic mean models of a speech recognizer are adapted into environmentally matched conditions by using the histogram equalization algorithm on a single utterance basis. For more robust speech recognition in the heavily noisy conditions, trained aco...

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 2016