A comparative study of mel cepstra and EIH for phone classification under adverse conditions

187

This paper presents a new approach to an auditory model for robust speech recognition in noisy environments. The proposed model consists of cochlear bandpass filters and nonlinear operations in which frequency information of the signal is obtained by zero-crossing intervals. Intensity information is also incorporated by a peak detector and a compressive nonlinearity. The robustness of the zero-crossings in spectral estimation is verified by analyzing the variance of the level-crossing intervals as a function of the crossing level values. Compared with other auditory models, the proposed auditory model is computationally efficient, free from many unknown parameters, and able to serve as a robust front-end for speech recognition in noisy environments. Experimental results of speech recognition demonstrate the robustness of the proposed method in various types of noisy environments.

Section: Incorporation Of Dynamic Features and Comparison With Sevmentioning

confidence: 99%

Auditory processing of speech signals for robust speech recognition in real-world noisy environments

Kim

Lee

Kil

1999

187

“…In those models, the auditory effects are emulated as accurately as possible according to the current understanding. Such trials have yielded systems that outperformed the MFCC, PLP and RASTA systems in speech recognition applications especially in the presence of noise and other adverse conditions [10], [17], [28]- [31], [39], [43], [50]. They, however, suffer from very slow processing that makes real-time software implementation, for the overall ASR system, difficult and uneconomic with the current state-of-the-art computation and storage powers [31].…”

mentioning

confidence: 99%

Robust auditory-based speech processing using the average localized synchrony detection

Ali

Spiegel

Müeller³

2002

In this paper, a new auditory-based speech processing system based on the biologically rooted property of the average localized synchrony detection (ALSD) is proposed. The system detects periodicity in the speech signal at Bark-scaled frequencies while reducing the response's spurious peaks and sensitivity to implementation mismatches, and hence presents a consistent and robust representation of the formants. The system is evaluated for its formant extraction ability while reducing spurious peaks. It is compared with other auditory-based and traditional systems in the tasks of vowel and consonant recognition on clean speech from the TIMIT database and in the presence of noise. The results illustrate the advantage of the ALSD system in extracting the formants and reducing the spurious peaks. They also indicate the superiority of the synchrony measures over the mean-rate in the presence of noise. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. Abstract-In this paper, a new auditory-based speech processing system based on the biologically rooted property of the average localized synchrony detection (ALSD) is proposed. The system detects periodicity in the speech signal at Bark-scaled frequencies while reducing the response's spurious peaks and sensitivity to implementation mismatches, and hence presents a consistent and robust representation of the formants. The system is evaluated for its formant extraction ability while reducing spurious peaks. It is compared with other auditory-based and traditional systems in the tasks of vowel and consonant recognition on clean speech from the TIMIT database and in the presence of noise. The results illustrate the advantage of the ALSD system in extracting the formants and reducing the spurious peaks. They also indicate the superiority of the synchrony measures over the mean-rate in the presence of noise.

“…5, is designed with conventional HMM's as a benchmark using MFCC and delta-MFCC features and being trained with five iterations of Baum-Welch (ML) algorithm. This HMM (ML) is comparable in performance with other similar classifiers (e.g., [25]), and gives 65.7% phone classification rate using five-mixture CI models (about the same as 66.2% reported in [25] with 32 mixtures). The second classifier, denoted by HMM 5 in Fig.…”

Section: Experiments and Model Evaluation Resultsmentioning

confidence: 66%

HMM-based speech recognition using state-dependent, discriminatively derived transforms on mel-warped DFT features

Chengalvarayan

Deng

1997

In the study reported in this paper, we investigate interactions of front-end feature extraction and back-end classification techniques in hidden Markov model-based (HMMbased) speech recognition. The proposed model focuses on dimensionality reduction of the mel-warped discrete fourier transform (DFT) feature space subject to maximal preservation of speech classification information, and aims at finding an optimal linear transformation on the mel-warped DFT according to the minimum classification error (MCE) criterion. This linear transformation, along with the HMM parameters, are automatically trained using the gradient descent method to minimize a measure of overall empirical error counts. A further generalization of the model allows integration of the discriminatively derived state-dependent transformation with the construction of dynamic feature parameters. Experimental results show that state-dependent transformation on mel-warped DFT features is superior in performance to the mel-frequency cepstral coefficients (MFCC's). An error rate reduction of 15% is obtained on a standard 39-class TIMIT phone classification task, in comparison with the conventional MCE-trained HMM using MFCC's that have not been subject to optimization during training.