Feature compensation technique for robust speech recognition in noisy environments
نویسندگان
چکیده
In this paper, we analyze the problems of the existing interacting multiple model (IMM) and spectral subtraction (SS) approaches and propose a new approach to overcome the problems of these algorithms. Our approach combines the IMM and SS techniques based on a soft decision for speech presence. Results reported on AURORA2 database show that proposed approach shows 14.26 % of average relative improvement compared to the IMM algorithm in the speech recognition experiments.
منابع مشابه
روشی جدید در بازشناسی مقاوم گفتار مبتنی بر دادگان مفقود با استفاده از شبکه عصبی دوسویه
Performance of speech recognition systems is greatly reduced when speech corrupted by noise. One common method for robust speech recognition systems is missing feature methods. In this way, the components in time - frequency representation of signal (Spectrogram) that present low signal to noise ratio (SNR), are tagged as missing and deleted then replaced by remained components and statistical ...
متن کاملAdaptive Parameter Compensation for Robust Hands-free Speech Recognition Using a Dual Beamforming Microphone Array
This paper proposes a parameter compensation technique to improve the performance of hands-free speech recognition in noisy environments. The technique employs a microphone array to perform spatial filtering on the noisy input signals. A dual beamformer is used to form an estimate of both the desired speech signal and also the combined noise signals. Additional enhancement to the the desired si...
متن کاملImproving the performance of MFCC for Persian robust speech recognition
The Mel Frequency cepstral coefficients are the most widely used feature in speech recognition but they are very sensitive to noise. In this paper to achieve a satisfactorily performance in Automatic Speech Recognition (ASR) applications we introduce a noise robust new set of MFCC vector estimated through following steps. First, spectral mean normalization is a pre-processing which applies to t...
متن کاملFeature 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 کاملFeature Compensation with Model-Based Estimation for Noise Masking
In this letter, we propose a new approach to estimate the degree of noise masking based on a sophisticated model for clean speech distribution. This measure, named as noise masking probability (NMP), is incorporated into the feature compensation technique to achieve robust speech recognition in noisy environments. Experimental results show that the proposed approach improves the performance of ...
متن کاملSpeech Enhancement with Applications in Speech Recognition
The objective of this research is to develop feature compensation techniques to make automatic speech recognition (ASR) systems more robust to noise distortions. The research is important as the performance of ASR systems degrades dramatically in adverse environments, and hence greatly limits the speech recognition application deployment. In this report, we aim to build a generic framework for ...
متن کامل