Glottal Features Research Articles

Particle swarm optimization based feature enhancement and feature selection for improved emotion recognition in speech and glottal signals.

In the recent years, many research works have been published using speech related features for speech emotion recognition, however, recent studies show that there is a strong correlation between emotional states and glottal features. In this work, Mel-frequency cepstralcoefficients (MFCCs), linear predictive cepstral coefficients (LPCCs), perceptual linear predictive (PLP) features, gammatone filter outputs, timbral texture features, stationary wavelet transform based timbral texture features and relative wavelet packet energy and entropy features were extracted from the emotional speech (ES) signals and its glottal waveforms(GW). Particle swarm optimization based clustering (PSOC) and wrapper based particle swarm optimization (WPSO) were proposed to enhance the discerning ability of the features and to select the discriminating features respectively. Three different emotional speech databases were utilized to gauge the proposed method. Extreme learning machine (ELM) was employed to classify the different types of emotions. Different experiments were conducted and the results show that the proposed method significantly improves the speech emotion recognition performance compared to previous works published in the literature.

A comparative study of glottal source estimation techniques

Abstract Source-tract decomposition (or glottal flow estimation) is one of the basic problems of speech processing. For this, several techniques have been proposed in the literature. However, studies comparing different approaches are almost nonexistent. Besides, experiments have been systematically performed either on synthetic speech or on sustained vowels. In this study we compare three of the main representative state-of-the-art methods of glottal flow estimation: closed-phase inverse filtering, iterative and adaptive inverse filtering, and mixed-phase decomposition. These techniques are first submitted to an objective assessment test on synthetic speech signals. Their sensitivity to various factors affecting the estimation quality, as well as their robustness to noise are studied. In a second experiment, their ability to label voice quality (tensed, modal, soft) is studied on a large corpus of real connected speech. It is shown that changes of voice quality are reflected by significant modifications in glottal feature distributions. Techniques based on the mixed-phase decomposition and on a closed-phase inverse filtering process turn out to give the best results on both clean synthetic and real speech signals. On the other hand, iterative and adaptive inverse filtering is recommended in noisy environments for its high robustness.

Detection of Clinical Depression in Adolescents’ Speech During Family Interactions

The properties of acoustic speech have previously been investigated as possible cues for depression in adults. However, these studies were restricted to small populations of patients and the speech recordings were made during patients' clinical interviews or fixed-text reading sessions. Symptoms of depression often first appear during adolescence at a time when the voice is changing, in both males and females, suggesting that specific studies of these phenomena in adolescent populations are warranted. This study investigated acoustic correlates of depression in a large sample of 139 adolescents (68 clinically depressed and 71 controls). Speech recordings were made during naturalistic interactions between adolescents and their parents. Prosodic, cepstral, spectral, and glottal features, as well as features derived from the Teager energy operator (TEO), were tested within a binary classification framework. Strong gender differences in classification accuracy were observed. The TEO-based features clearly outperformed all other features and feature combinations, providing classification accuracy ranging between 81%-87% for males and 72%-79% for females. Close, but slightly less accurate, results were obtained by combining glottal features with prosodic and spectral features (67%-69% for males and 70%-75% for females). These findings indicate the importance of nonlinear mechanisms associated with the glottal flow formation as cues for clinical depression.

The Distribution of Laryngeal Segments in Capanahua

The aim of this study is to enhance the documentation of laryngeal segments in Capanahua and to contribute to studies of the interaction between prosodic structure and segments. Laryngeal segments in Capanahua show a number of positional effects. They can only surface within morpheme‐initial syllables. This study shows that within that position, the distinction between head and nonhead syllables plays a major role in governing the alternations shown by glottal stops. Coda glottal stops can only surface in head‐syllables since they inhibit glottal coalescence, a process triggered elsewhere. In contrast, in nonhead syllables, glottal stops fuse with the preceding vowel, resulting in glottalized vowels. The underlying representations of morphemes can only contain one glottal feature; that is, either [constricted glottis] or [spread glottis] but not both. However, in Capanahua, this restriction does not hold at the level of phonetic representation since glottal stops and glottal fricatives co‐occur when the g...

Spoken emotion recognition through optimum-path forest classification using glottal features

A new method for the recognition of spoken emotions is presented based on features of the glottal airflow signal. Its effectiveness is tested on the new optimum path classifier (OPF) as well as on six other previously established classification methods that included the Gaussian mixture model (GMM), support vector machine (SVM), artificial neural networks – multi layer perceptron (ANN-MLP), k-nearest neighbor rule (k-NN), Bayesian classifier (BC) and the C4.5 decision tree. The speech database used in this work was collected in an anechoic environment with ten speakers (5 M and 5 F) each speaking ten sentences in four different emotions: Happy, Angry, Sad, and Neutral. The glottal waveform was extracted from fluent speech via inverse filtering. The investigated features included the glottal symmetry and MFCC vectors of various lengths both for the glottal and the corresponding speech signal. Experimental results indicate that best performance is obtained for the glottal-only features with SVM and OPF generally providing the highest recognition rates, while for GMM or the combination of glottal and speech features performance was relatively inferior. For this text dependent, multi speaker task the top performing classifiers achieved perfect recognition rates for the case of 6th order glottal MFCCs.

Critical Analysis of the Impact of Glottal Features in the Classification of Clinical Depression in Speech

The motivation for this work is in an attempt to rectify the current lack of objective tools for clinical analysis of emotional disorders. This study involves the examination of a large breadth of objectively measurable features for use in discriminating depressed speech. Analysis is based on features related to prosodics, the vocal tract, and parameters extracted directly from the glottal waveform. Discrimination of the depressed speech was based on a feature selection strategy utilizing the following combinations of feature domains: prosodic measures alone, prosodic and vocal tract measures, prosodic and glottal measures, and all three domains. The combination of glottal and prosodic features produced better discrimination overall than the combination of prosodic and vocal tract features. Analysis of discriminating feature sets used in the study reflect a clear indication that glottal descriptors are vital components of vocal affect analysis.

The Lexical and Post-Lexical Phonology of Thai Tones*

At first glance, the five-tone system of Thai looks quite simple. However, a detailed examination of the phonological distributions of segments and tones, combined with a careful analysis of the phonetic realizations of duration and pitch in both citation forms and connected speech, lead to the conclusion that the system is in fact complex and interesting. Based on data from an acoustic experiment, we claim that the tone bearing unit in Thai is the mora, and that previously unexplained restrictions on the distributions of tones in syllables closed by obstruents are the result of a relationship between the glottal feature and low tones. We describe and explain unexpected differences in the realization of tones in different phrasal positions in connected speech, and show that there are non-neutralizing contour tone simplifications that take place non-finally at the post-lexical level. Our analysis combines descriptive phonetics and phonology with both representational and constraint-based explanations (incorporating positional faithfulness and stratal Optimality Theory) to provide a unified account of the Thai tonal system. Our study supports a view of the grammar in which phonetics and phonology are separate, yet intricately related.

Modeling of the glottal flow derivative waveform with application to speaker identification

An automatic technique for estimating and modeling the glottal flow derivative source waveform from speech, and applying the model parameters to speaker identification, is presented. The estimate of the glottal flow derivative is decomposed into coarse structure, representing the general flow shape, and fine structure, comprising aspiration and other perturbations in the flow, from which model parameters are obtained. The glottal flow derivative is estimated using an inverse filter determined within a time interval of vocal-fold closure that is identified through differences in formant frequency modulation during the open and closed phases of the glottal cycle. This formant motion is predicted by Ananthapadmanabha and Fant (1982) to be a result of time-varying and nonlinear source/vocal tract coupling within a glottal cycle. The glottal flow derivative estimate is modeled using the Liljencrants-Fant (1986) model to capture its coarse structure, while the fine structure of the flow derivative is represented through energy and perturbation measures. The model parameters are used in a Gaussian mixture model speaker identification (SID) system. Both coarse- and fine-structure glottal features are shown to contain significant speaker-dependent information. For a large TIMIT database subset, averaging over male and female SID scores, the coarse-structure parameters achieve about 60% accuracy, the fine-structure parameters give about 40% accuracy, and their combination yields about 70% correct identification. Finally, in preliminary experiments on the counterpart telephone-degraded NTIMIT database, about a 5% error reduction in SID scores is obtained when source features are combined with traditional mel-cepstral measures.

Three Glottal Features

Evidence for laryngeal control mechanisms may be obtained from observations of the states of the glottis that can be used to produce linguistic contrasts in the languages of the world. All languages use differences in pitch, which are produced by controlling the glottal tersion. All languages contrast voiced and voiceless sounds. Some languages also have breathy voiced sounds, others also have creaky voiced sounds, others contrast stiff voice and slack voice, etc. But no language contrasts more than three of these phonation types. This constraint on languages can be explained by setting up a single feature, glottal stricture, on which only three distinctions can be made at a time. This feature is controlled primarily by the distance between the arytenoid cartilages, which is smallest in a glottal stop and increases through creaky voice, stiff voice, voice, slack voice, and breathy voice, until it reaches its maximum in voiceless sounds. The third feature, which is used by many languages, is glottal timing, or voice onset time, which distinguishes aspirated from unaspirated sounds.