The goal of this paper is to discuss comparison of speech parameterization methods: Mel-Frequency Cepstrum Coefficients (MFCC) and Linear Prediction Cepstrum Coefficients (LPCC) for recognizing the stuttered events. Speech samples from UCLASS are used for our analysis. The stuttered events are identified through manual segmentation and used for feature extraction. Two simple classifiers are used for testing the proposed features. Conventional validation method is used for testing the reliability of the classifier. The experimental investigation elucidates MFCC and LPCC features which can be used for identifying the stuttered events and LPCC features were slightly outperformed than MFCC features.

Classification of speech dysfluencies with MFCC and LPCC features

Speech is a complex naturally acquired human motor ability. It is characterized in adults with the production of about 14 different sounds per second via the harmonized actions of roughly 100 muscles. Speaker recognition is the capability of a software or hardware to receive speech signal, identify the speaker present in the speech signal and recognize the speaker afterwards. Feature extraction is accomplished by changing the speech waveform to a form of parametric representation at a relatively minimized data rate for subsequent processing and analysis. Therefore, acceptable classification is derived from excellent and quality features. Mel Frequency Cepstral Coefficients (MFCC), Linear Prediction Coefficients (LPC), Linear Prediction Cepstral Coefficients (LPCC), Line Spectral Frequencies (LSF), Discrete Wavelet Transform (DWT) and Perceptual Linear Prediction (PLP) are the speech feature extraction techniques that were discussed in these chapter. These methods have been tested in a wide variety of applications, giving them high level of reliability and acceptability. Researchers have made several modifications to the above discussed techniques to make them less susceptible to noise, more robust and consume less time. In conclusion, none of the methods is superior to the other, the area of application would determine which method to select.

/pdf/some-commonly-used-speech-feature-extraction-algorithms-5fbw1gtwuf.pdf

Some Commonly Used Speech Feature Extraction Algorithms

Stuttering is a speech disorder in which the normal flow of speech is disrupted by occurrences of dysfluencies, such as repetitions, interjection and so on. There are a high proportion of repetitions and prolongations in stuttered speech, usually at the beginning of sentences. Consequently, acoustic analysis can be used to classify the stuttered events. This paper describes particular stuttering events to be located as repetitions and prolongations in stuttered speech with feature extraction algorithm. The well known Mel Frequency Cepstral Coefficient (MFCC) feature extraction is implemented to test its effectiveness in recognizing prolongations and repetitions in a stuttered speech. In this work, two classifiers such as Linear Discriminant Analysis based classifier (LDA) and ?-nearest neighbors (Λ-1Ν1Ν) are employed and ?-fold cross-validation was applied to measure classifiers performances. The result of this work shows that the MFCC and classifiers (LDA and Λ-1Ν1Ν) can be used for recognition of repetitions and prolongations in stuttered speech with the average accuracy of 90%.

MFCC based recognition of repetitions and prolongations in stuttered speech using k-NN and LDA

The goal of this paper is to discuss and compare three feature extraction methods: Linear Predictive Coefficients (LPC), Linear Prediction Cepstral Coefficients (LPCC) and Weighted Linear Prediction Cepstral Coefficients (WLPCC) for recognizing the stuttered events. Speech samples from the University College London Archive of Stuttered Speech (UCLASS) were used for our analysis. The stuttered events were identified through manual segmentation and were used for feature extraction. Two simple classifiers namely, k-nearest neighbour (kNN) and Linear Discriminant Analysis (LDA) were employed for speech dysfluencies classification. Conventional validation method was used for testing the reliability of the classifier results. The study on the effect of different frame length, percentage of overlapping, value of a in a first order pre-emphasizer and different order p were discussed. The speech dysfluencies classification accuracy was found to be improved by applying statistical normalization before feature extraction. The experimental investigation elucidated LPC, LPCC and WLPCC features can be used for identifying the stuttered events and WLPCC features slightly outperforms LPCC features and LPC features.

Classification of Speech Dysfluencies Using LPC Based Parameterization Techniques

Stuttering is a speech disorder in which the normal flow of speech is disrupted by occurrences of dysfluencies, such as repetitions, interjection and so on. There are high proportion of repetitions and prolongations in stuttered speech, usually at the beginning of sentences. Consequently, acoustic analysis can be used to classify the stuttered events. This paper describes particular stuttering events to be located as repetitions and prolongations in stuttered speech with feature extraction algorithm. Linear Predictive Cepstral Coefficient (LPCC) feature extraction is implemented to test its effectiveness in recognizing prolongations and repetitions in stuttered speech. In this work, two classifiers, Linear Discriminant Analysis classifier (LDA) and k-nearest neighbors (k-NN) are employed. Result shows that the LPCC and classifier (LDA and k-NN) can be used for the recognition of repetitions and prolongations in stuttered speech with the best accuracy of 89.77%.

Automatic detection of prolongations and repetitions using LPCC

Automatic detection of syllable repetition is one of the important parameter in assessing the stuttered speech objectively. The existing method which uses artificial neural network (ANN) requires high levels of agreement as prerequisite before attempting to train and test ANNs to separate fluent and nonfluent. We propose automatic detection method for syllable repetition in read speech for objective assessment of stuttered disfluencies which uses a novel approach and has four stages comprising of segmentation, feature extraction, score matching and decision logic. Feature extraction is implemented using well know Mel frequency Cepstra coefficient (MFCC). Score matching is done using Dynamic Time Warping (DTW) between the syllables. The Decision logic is implemented by Perceptron based on the score given by score matching. Although many methods are available for segmentation, in this paper it is done manually. Here the assessment by human judges on the read speech of 10 adults who stutter are described using corresponding method and the result was 83%. Keywords—Assessment, DTW, MFCC, Objective, Perceptron, Stuttering.

/pdf/automatic-detection-of-syllable-repetition-in-read-speech-523o6le2vj.pdf

R. Rajagopal

Papers

Automatic Detection of Syllable Repetition in Read Speech for Objective Assessment of Stuttered Disfluencies