Speech Recognition in Noisy Environment-an implementation on MATLAB

نویسندگان

  • Nishitha Danthi
  • Dayananda Sagar
چکیده

Speech is one of the ways to express ourselves naturally. So, speech can be used as a means to communicate with machines. In this work, using MATLAB as a platform isolated word recognizer is achieved. Speech signals get distorted by many kinds of noises. Hence, it is necessary to reduce the noise contained in the speech signal. This is called speech enhancement. Speech enhancement aims at improving the intelligibility of the speech. Noise has been removed using Spectral Subtraction with Over Subtraction technique. The feature extraction is carried out using MFCC and feature matching is achieved using HMM.

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

Speech Emotion Recognition Based on Power Normalized Cepstral Coefficients in Noisy Conditions

Automatic recognition of speech emotional states in noisy conditions has become an important research topic in the emotional speech recognition area, in recent years. This paper considers the recognition of emotional states via speech in real environments. For this task, we employ the power normalized cepstral coefficients (PNCC) in a speech emotion recognition system. We investigate its perfor...

متن کامل

An Information-Theoretic Discussion of Convolutional Bottleneck Features for Robust Speech Recognition

Convolutional Neural Networks (CNNs) have been shown their performance in speech recognition systems for extracting features, and also acoustic modeling. In addition, CNNs have been used for robust speech recognition and competitive results have been reported. Convolutive Bottleneck Network (CBN) is a kind of CNNs which has a bottleneck layer among its fully connected layers. The bottleneck fea...

متن کامل

Extracting GFCC Features for Emotion Recognition from Audio Speech Signals

A major challenge for automatic speech recognition (ASR) relates to significant performance reduction in noisy environments. This paper presents our implementation of the Gammatone frequency cepstral coefficients (GFCCs) filter-based feature along with BPNN and the experimental results on English speech data. By some thorough designs, we obtained significant performance gains with the new featu...

متن کامل

Isolated Telugu Speech Recognition using MFCC and Gamma tone features by Radial Basis Networks in Noisy Environment

In this paper, Radial basis neural networks[1][12][17] have been examined for speech recognition using speech features MFCC (Mel frequency Coefficients) and Gamma tone frequency coefficients for isolated Telugu words in noisy environment. Speech feature vectors are used to train, validate and test the Radial basis neural networks.Experiments conducted in Office environment under the presence of...

متن کامل

Extracting MFCC Features For Emotion Recognition From Audio Speech Signals

A major challenge for automatic speech recognition (ASR) relates to significant performance reduction in noisy environments. Recent research has shown that auditory features based on Gammatone filters are promising to improve robustness of ASR systems against noise, though the research is far from extensive and generalizability of the new features is unknown. This paper presents our implementat...

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 2017