No abstract

Automatic detection of voice pathology enables objective assessment and earlier intervention for the diagnosis. This study provides a systematic analysis of glottal source features and investigates their effectiveness in voice pathology detection. Glottal source features are extracted using glottal flows estimated with the quasi-closed phase (QCP) glottal inverse filtering method, using approximate glottal source signals computed with the zero frequency filtering (ZFF) method, and using acoustic voice signals directly. In addition, we propose to derive mel-frequency cepstral coefficients (MFCCs) from the glottal source waveforms computed by QCP and ZFF to effectively capture the variations in glottal source spectra of pathological voice. Experiments were carried out using two databases, the Hospital Universitario Príncipe de Asturias (HUPA) database and the Saarbrücken Voice Disorders (SVD) database. Analysis of features revealed that the glottal source contains information that discriminates normal and pathological voice. Pathology detection experiments were carried out using support vector machine (SVM). From the detection experiments it was observed that the performance achieved with the studied glottal source features is comparable or better than that of conventional MFCCs and perceptual linear prediction (PLP) features. The best detection performance was achieved when the glottal source features were combined with the conventional MFCCs and PLP features, which indicates the complementary nature of the features.

Speech carries information not only about the lexical content, but also about the age, gender, signature and emotional state of the speaker. Speech in different emotional states is accompanied by distinct changes in the production mechanism. In this chapter, we present a review of analysis methods used for emotional speech. In particular, we focus on the issues in data collection, feature representations and development of automatic emotion recognition systems. The significance of the excitation source component of speech production in emotional states is examined in detail. The derived excitation source features are shown to carry the emotion correlates. IntroductionHumans have evolved various forms of communication like facial expressions, gestures, body postures, speech, etc. The form of communication depends on the context of interaction, and is often accompanied by various physiological reactions such as changes in the heart rate, skin resistance, temperature, muscle activity and blood pressure. All forms of human communication carry information at two levels, the message and the underlying emotional state.Emotions are essential part of real life communication among human beings. Various descriptions of the term emotion are studied in [21,22,60,88,92,98,100]. Some of the descriptions are: (a) "Emotions are underlying states which are evolved and adaptive. Emotion expressions are produced by the communicative value of underlying states" [22].

The ASVspoof 2017 challenge is about the detection of replayed speech from human speech. The proposed system makes use of the fact that when the speech signals are replayed, they pass through multiple channels as opposed to original recordings. This channel information is typically embedded in low signal to noise ratio regions. A speech signal processing method with high spectro-temporal resolution is required to extract robust features from such regions. The single frequency filtering (SFF) is one such technique, which we propose to use for replay attack detection. While SFF based feature representation was used at front-end, Gaussian mixture model and bi-directional long short-term memory models are investigated at the backend as classifiers. The experimental results on ASVspoof 2017 dataset reveal that, SFF based representation is very effective in detecting replay attacks. The score level fusion of back end classifiers further improved the performance of the system which indicates that both classifiers capture complimentary information.

In this paper, we consider breathy to tense voices, which are often considered to be opposite ends of a voice quality continuum. Along with these, other aspects of a speaker's voice play an important role to convey the information to the listener such as mood, attitude and emotional state. The glottal pulse characteristics in different phonation types vary due to the tension of laryngeal muscles together with the respiratory effort. In the present study, we are deriving the features that can capture effects of excitation on the vocal tract system through a signal processing method, called as zero-time windowing (ZTW) method. The ZTW method gives the instantaneous spectrum which captures the changes in the speech production mechanism, providing higher spectral resolution. The cepstral coefficients derived from ZTW method are used for the classification of phonation types. Along with zero-time windowing cepstral coefficients (ZTWCCs), we use the excitation source features derived from zero frequency filtering (ZFF) method. The excitation features used are: strength of excitation, energy of excitation, loudness measure and ZFF signal energy. Classification experiments using ZTWCC and excitation features reveal a significant improvement in the detection of phonation type compared to the existing voice quality features and MFCC features.

No abstract

Parkinson's disease (PD) is a progressive deterioration of the human central nervous system. Detection of PD (discriminating patients with PD from healthy subjects) from speech is a useful approach due to its non-invasive nature. This study proposes to use novel cepstral coefficients derived from the single frequency filtering (SFF) method, called as single frequency filtering cepstral coefficients (SFFCCs) for the detection of PD. SFF has been shown to provide higher spectro-temporal resolution compared to the short-time Fourier transform. The current study uses the PC-GITA database, which consists of speech from speakers with PD and healthy controls (50 males, 50 females). Our proposed detection system is based on the i-vectors derived from SFFCCs using SVM as a classifier. In the detection of PD, better performance was achieved when the ivectors were computed from the proposed SFFCCs compared to the popular conventional MFCCs. Furthermore, we investigated the effect of temporal variations by deriving the shifted delta cepstral (SDC) coefficients using SFFCCs. These experiments revealed that the i-vectors derived from the proposed SF-FCCs+SDC features gave an absolute improvement of 9% compared to the i-vectors derived from the baseline MFCCs+SDC features, indicating the importance of temporal variations in the detection of PD.

A new method for robust estimation of fundamental frequency (F0) from speech signal is proposed in this paper. The method exploits the high SNR regions of speech in time and frequency domains in the outputs of single frequency filtering (SFF) of speech signal. The high resolution in the frequency domain brings out the harmonic characteristics of speech clearly. The harmonic spacing in the high SNR regions of spectrum determine the F0. The concept of root cepstrum is used to reduce the effects of vocal tract resonances in the F0 estimation. The proposed method is evaluated for clean speech and noisy speech simulated for 15 different degradations at different noise levels. Performance of the proposed method is compared with four other standard methods of F0 extraction. From the results it is evident that the proposed method is robust for most types of degradations.