A PESQ-based Performance Prediction Method for Noisy Speech Recognition
نویسندگان
چکیده
This paper investigates the relationship between the word accuracy and the PESQ (ITU-T Recommendation P.862) score, and the availability of the artificial voice (ITU-T Recommendation P.50) for calculating the PESQ score. For this purpose, recognition experiments using four noise reduction algorithms were performed on the AURORA-2J connected digit recognition task. These results confirmed that there is a strong correlation between the word accuracy and the PESQ score calculated from the real speech and the artificial voice.
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 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 کاملPerformance Estimation of Noisy Speech Recognition Considering the Accuracy of Acoustic Models
To ensure a satisfactory QoE (Quality of Experience) and facilitate system design in speech recognition services, it is essential to establish a method that can be used to efficiently investigate recognition performance in different noise environments. Previously, we proposed a performance estimation method using the PESQ (Perceptual Evaluation of Speech Quality) as a measure of speech distorti...
متن کاملConditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks (GANs) in a variety of image processing tasks, we explore the potential of conditional GANs (cGANs) for SE, and in particular, we make use of the image proc...
متن کاملAn 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