Improving the Robustness of LPCC Feature Against Impulsive Noise by Applying the FOP Method
نویسنده
چکیده
Performance of an automatic speech recognition (ASR) system tends to be dramatically degraded in the presence of impulsive noise. In the previous work [1], we proposed flooring the observation probability (FOP) to compensate the adverse effect of impulsive noise on sensitive dimensions of Mel-frequency cepstral coefficient (MFCC) features. Linear prediction cepstral coefficient (LPCC) is another kind of widely used acoustic feature, and in this paper we study the performance of the FOP method when applied to LPCC features, including feature vector partition based upon noise sensitivity analysis of each feature dimension and flooring threshold calculation. Evaluation results confirm the efficiency of FOP method on LPCC feature. For example, the highest averaged error reduction rate (ERR) of 38.9% and 46.8% versus the baseline is obtained, respectively in simulated substitutive impulsive noise and machinegun noise environment.
منابع مشابه
Soft decision strategy and adaptive compensation for robust speech recognition against impulsive noise
This paper presents research on robust automatic speech recognition (ASR) in the presence of impulsive noise, which is usually caused by transmission errors or packet loss in network-based delivery of speech signals. A soft decision strategy is proposed by analyzing the degraded observation probabilities caused by impulsive noise. Based on the soft decision results, two compensation methods are...
متن کاملImproving the filter bank of a classic speech feature extraction algorithm
The most popular speech feature extractor used in automatic speech recognition (ASR) systems today is the mel frequency cepstral coefficient (mfcc) algorithm. Introduced in 1980, the filter bank-based algorithm eventually replaced linear prediction cepstral coefficients (lpcc) as the premier front end, primarily because of mfcc’s superior robustness to additive noise. However, mfcc does not app...
متن کاملRobust Speech Perception Hashing Authentication Algorithm Based on Spectral Subtraction and Multi-feature Tensor
In order to make the speech perception hashing authentication algorithm has strong robustness and discrimination to content preserving operations and speech communication under the common background noise, a new robust speech perceptual hashing authentication algorithm based on spectral subtraction and multi-feature tensor was proposed. The proposed algorithm uses spectral subtraction method to...
متن کاملA Comparative Study Of LPCC And MFCC Features For The Recognition Of Assamese Phonemes
In this paper two popular feature extraction techniques Linear Predictive Cepstral Coefficients (LPCC) and Mel Frequency Cepstral Coefficients (MFCC) have been investigated and their performances have been evaluated for the recognition of Assamese phonemes. A multilayer perceptron based baseline phoneme recognizer has been built and all the experiments have been carried out using that recognize...
متن کاملImpulsive Noise Elimination Considering the Bit Planes Information of the Image
Impulsive noise is one of the imposed defectives degrades the quality of images. Performance of many image processing applications directly depends on the quality of the input image. Hence, it is necessary to de-noise the degraded images without losing their valuable information such as edges. In this paper we propose a method to remove impulsive noise from color images without damaging the ima...
متن کامل