Human Factor Cepstral Coefficients Research Articles

Recognition of Pathological Voices by Human Factor Cepstral Coefficients (HFCC)

Human speech is a means of communication that is very important in our daily lives. It is characterized by its great ability to transmit our ideas, our emotions, our personality etc. So, any alteration of the voice can prevent the person from exercising his professional and daily life naturally. It is for these reasons that it is very necessary to implement systems for detecting and classifying vocal pathologies. These automatic systems can help clinicians customize and detect the existence of any vocal pathology. In this context, several tools have been introduced to achieve early detection of voice disorders. Among these tools are the Human Factor Cepstral Coefficients (HFCC) combined with prosodic parameters, the Noise-Harmonic Ratio (NHR), the Harmonic-Noise Ratio (HNR), analysis of trend Fluctuations (DFA) and Fundamental frequency (F0). These parameters are introduced and calculated in every frame. In this study, we used a variation of HFCC called Equivalent Rectangular Bandwidth (ERB) to study the effects of HFCC on the classification of pathological voices. Using the HTK classifiers, the classification is carried out on two pathological databases, Massachusetts Eye and Ear Infirmary (MEEI) and Saarbruecken Voice Database (SVD). To assess the performance of the system, we used sensitivity and specificity.

Speech emotion recognition using cepstral features extracted with novel triangular filter banks based on bark and ERB frequency scales

Speech emotion recognition (SER) refers to the process of recognizing the emotional state of the speaker from the speech utterance. In earlier studies, wide varieties of cepstral features have been proposed to develop SER systems. The mel-frequency cepstral coefficients (MFCC), and human-factor cepstral coefficients (HFCC) are two popularly used variants of cepstral features. MFCC and HFCC features are extracted from speech signals using mel and human-factor filter banks, respectively. The magnitude response of individual filters in these filter banks is triangular in shape. As a result, these filter banks are referred to as triangular filter banks (TFB) and the corresponding extracted cepstral coefficients can be denoted as TFBCC-M (in case of MFCC) and TFBCC-HF (in case of HFCC). The mel-filter bank (TFB-M) is constructed using mel-scale, while the human-factor filter bank (TFB-HF) is constructed using human factor scale, which is a combination of mel and equivalent rectangular bandwidth (ERB) scales. Similarly, different frequency scales can be used to realize different TFBs to extract different types of TFBCC features. In this direction, this paper proposes two new TFBs denoted as TFB-B and TFB-E, realized using bark and ERB scales to extract new cepstral features referred to as TFBCC-B and TFBCC-E, respectively. The mathematical background to construct the proposed TFB-B and TFB-E is presented. The proposed filter banks are used along with the conventional TFB-M and TFB-HF to extract four different types of TFBCC features. These features are extracted from the emotional speech signals of two databases, namely Berlin database of emotional speech (Emo-DB) and Surrey audio-visual expressed emotion speech database (SAVEE). The extracted features are used to develop speaker-dependent (SD) and speaker-independent (SI) based SER systems using support vector machines. The performance of the respective features is analyzed in terms of isolated and combined usage. The experimental results show that the cepstral features extracted using the proposed TFBs are effective in characterizing and recognizing emotions similar to conventional MFCC and HFCC features. Moreover, the combined use of different cepstral features have resulted to improve the overall recognition performance of SER systems. In case of Emo-DB database, isolated use of the proposed TFBCC-B and TFBCC-E features achieve recognition accuracies of 83.23% and 81.99% for SD scenario, and 75% and 60.94% for SI scenario, respectively. Similarly, for SAVEE database, the recognition accuracies of 75% and 66.67% for SD scenario, and 44.17% and 55% for SI scenario are achieved. In case of Emo-DB database, the maximum recognition accuracies of 86.96% (for different combinations of conventional and proposed features namely, TFBCC-{(M+E), (M+B+E), (HF+B+E), (M+HF+B+E)}) and 77.08% (for combination TFBCC-(M+B+E)) are achieved for SD and SI scenarios, respectively. Similarly, for SAVEE database, the maximum recognition accuracies of 77.08% (for combination TFBCC-(M+HF+E)), and 55.83% (for combination TFBCC-(B+E)) are achieved for SD and SI scenarios, respectively.

Automatic bird species recognition based on birds vocalization

This paper deals with a project of Automatic Bird Species Recognition Based on Bird Vocalization. Eighteen bird species of 6 different families were analyzed. At first, human factor cepstral coefficients representing the given signal were calculated from particular recordings. In the next phase, using the voice activity detection system, segments of bird vocalizations were detected from which a likelihood rate, with which the given code value corresponds to the given model, was calculated using individual hidden Markov models. For each bird species, just one respective hidden Markov model was trained. The interspecific success of 81.2% has been reached. For classification into families, the success has reached 90.45%.

Feature Extraction Analysis for Hidden Markov Models in Sundanese Speech Recognition

Sundanese language is one of the popular languages in Indonesia. Thus, research in Sundanese language becomes essential to be made. It is the reason this study was being made. The vital parts to get the high accuracy of recognition are feature extraction and classifier. The important goal of this study was to analyze the first one. Three types of feature extraction tested were Linear Predictive Coding (LPC), Mel Frequency Cepstral Coefficients (MFCC), and Human Factor Cepstral Coefficients (HFCC). The results of the three feature extraction became the input of the classifier. The study applied Hidden Markov Models as its classifier. However, before the classification was done, we need to do the quantization. In this study, it was based on clustering. Each result was compared against the number of clusters and hidden states used. The dataset came from four people who spoke digits from zero to nine as much as 60 times to do this experiments. Finally, it showed that all feature extraction produced the same performance for the corpus used.

Using Human Factor Cepstral Coefficient on Multiple Types of Voice Recordings for Detecting Patients with Parkinson's Disease

In this study, we wanted to discriminate between two groups of participants (patients with Parkinson's disease and healthy people) by analyzing 3 types of voice recordings. Firstly we collected multiple types of voice recording of three sustained vowels /a/, /o/ and /u/ at a comfortable level which was collected from the 40 participants (20 PD and 20 healthy). The technique used in this study is to extract Human Factor Cepstral Coefficients (HFCC). The extracted HFCC were compressed by calculating their average value in order to get the Voiceprint from each voice recording. Subsequently, a classification method was performed using Leave One Subject Out validation scheme along with supervised learning classifiers. We used SVM with its four different kernels (RBF, Linea, Polynomial and MLP), and k-nearest neighbored (k=3, 5 and 7). Based on the research result, the best obtained classification accuracy was 87.5% using linear kernel of SVM with the first 14 cepstral coefficients of the HFCC and 100% using the test database.

Evaluation of various feature sets and feature selection towards automatic recognition of bird species

It is necessary to develop efficient methods for monitoring and recognising bird species that will help in evaluating the biodiversity of a region. In this paper we present techniques for automatic recognition of bird species based on audio recordings of their sounds. In this work, various audio features like descriptive features, wavelet packet decomposition-based features and perceptual features like Mel-frequency cepstral coefficients, perceptual linear prediction, and human factor cepstral coefficients are evaluated. Combination of these feature sets has also been evaluated. Classification of ten bird species is carried out using Gaussian Mixture Modelling (GMM) and Support Vector Machines (SVMs). When a number of features are extracted, the feature vector may contain redundancy. Redundant features may either degrade the performance of the system or add no value to the system. For feature subset selection, this work implements a technique based on singular value decomposition and QR decomposition using column pivoting.

Evaluation of various feature sets and feature selection towards automatic recognition of bird species

It is necessary to develop efficient methods for monitoring and recognising bird species that will help in evaluating the biodiversity of a region. In this paper we present techniques for automatic recognition of bird species based on audio recordings of their sounds. In this work, various audio features like descriptive features, wavelet packet decomposition-based features and perceptual features like Mel-frequency cepstral coefficients, perceptual linear prediction, and human factor cepstral coefficients are evaluated. Combination of these feature sets has also been evaluated. Classification of ten bird species is carried out using Gaussian Mixture Modelling (GMM) and Support Vector Machines (SVMs). When a number of features are extracted, the feature vector may contain redundancy. Redundant features may either degrade the performance of the system or add no value to the system. For feature subset selection, this work implements a technique based on singular value decomposition and QR decomposition using column pivoting.

Effect of speech tasks on cepstral measures of articulation

Hypokinesia in articulatory movements is one of the predominant characteristics in individuals with Parkinson’s disease (PD). Past research quantified such hypokinesias through measures of formant frequencies (F1 and F2) and/or derivative measures such as vowel space area. Extractions of these acoustic measures are labor intensive, time consuming and require phonetic segmentation. In this study, we characterize acoustic measures of articulatory range, rate and acceleration using human factor cepstral coefficients (HFCCs) across speech tasks (e.g. syllable repetition, sentence reading and monologues). Cepstral measures of articulation can be readily derived from entire sentences in an automated, time/computationally efficient method. We hypothesize that these cepstral measures will show a significant effect of group and speech task. Twelve individuals with clinical diagnosis of idiopathic PD and age/gender matched healthy controls repeated syllables at a fast rate, read some sentences, and provided monologue samples. Articulatory range, rate and acceleration were studied using cepstral coefficient standard deviation sum (CC SDS), delta (Δ), and delta delta (ΔΔ) coefficients, respectively. Preliminary findings suggest that temporal derivatives differentiated the groups better in the syllable repetition task and CC SDS revealed trends in the reading and monologue tasks, showing promise for differential and early diagnosis.

Automatic Recognition of Pathological Phoneme Production

Objective: Proper diagnosis and therapy of pathological pronunciation of phonemes play an important role in modern logopedics. To enhance the efficiency of diagnosis and therapy an automatic recognition of pathological phoneme pronunciation is addressed in this paper. The authors focus on the therapy of phoneme substitution disorders. Patients and Methods: Recognized speech samples come from speech-impaired Polish children and partially from persons imitating speech disorders. Recognized speech disorders were substitutions in pairs {s, ʂ}, {ɕ, ʂ}, {ʦ, tʂ+}, {ʨ, tʂ+}, {ʣ, dʐ+ }, and {ʥ, dʐ+ } embedded in Polish carrier words. In order to detect substitutions in the recognized words, recently proposed human factor cepstral coefficients (HFCC) have been implemented. Efficiency of the HFCC approach was compared to the application of standard mel-frequency cepstral coefficients (MFCC) as a feature vector. Both dynamic time warping (DTW), working on whole words or embedded phoneme patterns, and hidden Markov models (HMM) were used as classifiers. The HMM classifier was based on whole-word models as well as phoneme models. Results present a comparative analysis of DTW and HMM methods. Conclusions: The superiority of HFCC features over those of MFCC was demonstrated. Results obtained by DTW methods, mainly by modified phoneme-based DTW classifier, were slightly better in comparison with the HMM classifier. Results obtained for the detection of substitution in pairs {s, ʂ}, {ʦ, tʂ+}, {ʣ, ʣ+ } are very promising. The methods developed for these cases can be integrated into computer systems for speech therapy. For substitutions in pairs {ɕ, ʂ}, {ʨ, tʂ+}, {ʥ, dʐ+ } further research is necessary.

The application of a psychophysical difference metric to perceptual similarity judgments in vowels

Models of cross-language speech perception have had limited success in predicting the discriminability or perceptual similarity of non-native contrasts. These failures may be attributed partly to an inability to quantify the phonetic differences between non-native speech sounds. This study attempted to quantify such gross psychophysical differences between speech sounds, specifically by utilizing dynamic time warping (DTW) on human factor cepstral coefficients to compare the spectrum of the entire length of the speech sounds in question. This technique has been successfully applied to account for the discriminability of different non-native consonant contrasts [Harnsberger, J. D., Shrivastav, R., and Skowronski, M.; J. Acous. Soc. Am. 117, 2460, 2005]. This study extends this work to perceptual similarity judgments of vowels. Specifically, twenty native speakers of English were presented with all possible pairings of ten vowels produced by two speakers of English. Subjects were asked to rate their similarity on a seven point scale. The resulting similarity scores were then compared with the output matrix of the DTW psychophysical difference metric for the same stimulus materials. The results showed a significant correlation (r=.60**) between the two measures, demonstrating the efficacy of the metric with a greater range of stimulus types and tasks.

Exploiting independent filter bandwidth of human factor cepstral coefficients in automatic speech recognition.

Mel frequency cepstral coefficients (MFCC) are the most widely used speech features in automatic speech recognition systems, primarily because the coefficients fit well with the assumptions used in hidden Markov models and because of the superior noise robustness of MFCC over alternative feature sets such as linear prediction-based coefficients. The authors have recently introduced human factor cepstral coefficients (HFCC), a modification of MFCC that uses the known relationship between center frequency and critical bandwidth from human psychoacoustics to decouple filter bandwidth from filter spacing. In this work, the authors introduce a variation of HFCC called HFCC-E in which filter bandwidth is linearly scaled in order to investigate the effects of wider filter bandwidth on noise robustness. Experimental results show an increase in signal-to-noise ratio of 7 dB over traditional MFCC algorithms when filter bandwidth increases in HFCC-E. An important attribute of both HFCC and HFCC-E is that the algorithms only differ from MFCC in the filter bank coefficients: increased noise robustness using wider filters is achieved with no additional computational cost.

Human factor cepstral coefficients

Automatic speech recognition (ASR) is an emerging field with the goal of creating a more natural man/machine interface. The single largest obstacle to widespread use of ASR technology is robustness to noise. Since human speech recognition greatly outperforms current ASR systems in noisy environments, ASR systems seek to improve noise robustness by drawing on biological inspiration. Most ASR front ends employ mel frequency cepstral coefficients (mfcc) which is a filter bank-based algorithm whose filters are spaced on a linear-log frequency scale. Although center frequency is based on a perceptually motivated frequency scale, filter bandwidth is set by filter spacing and not through biological motivation. The coupling of filter bandwidth to other filter bank parameters (frequency range, number of filters) has led to variations of the original algorithm with different filter bandwidths. In this work, a novel extension to mfcc is introduced which decouples filter bandwidth from the rest of the filter bank parameters by employing the relationship between filter center frequency and critical bandwidth of the human auditory system. The new algorithm, called human factor cepstral coefficients (hfcc), is shown to outperform the original mfcc and two popular variations in several ASR experiments and noise sources.