Visual voice activity detection using frontal versus profile views

Visual activity detection of lip movements can be used to overcome the poor performance of voice activity detection based solely in the audio domain, particularly in noisy acoustic conditions. However, most of the research conducted in visual voice activity detection (VVAD) has neglected addressing variabilities in the visual domain such as viewpoint variation. In this paper we investigate the effectiveness of the visual information from the speaker’s frontal and profile views (i.e left and right side views) for the task of VVAD. As far as we are aware, our work constitutes the first real attempt to study this problem. We describe our visual front end approach and the Gaussian mixture model (GMM) based VVAD framework, and report the experimental results using the freely available CUAVE database. The experimental results show that VVAD is indeed possible from profile views and we give a quantitative comparison of VVAD based on frontal and profile views The results presented are useful in the development of multi-modal Human Machine Interaction (HMI) using a single camera, where the speaker’s face may not always be frontal.

Tuning of modulation spectrum parameters for voice pathology detection

Acoustic parameters are frequently used to assess the presence of pathologies in human voice. Many of them have demonstrated to be useful but in some cases its results could be optimized by selecting appropriate working margins. In this study two indices, CIL and RALA, obtained from Modulation Spectra are described and tuned using different frame lengths and frequency ranges to maximize AUC in normal to pathological voice detection. After the tuning process, AUC reaches 0.96 and 0.95 values for CIL and RALA respectively representing an improvement of 16 % and 12 % at each case respect to the typical tuning based only on frame length selection.

GMM-based classifiers for the automatic detection of obstructive sleep apnea

The aim of automatic pathological voice detection systems is to serve as tools, to medical specialists, for a more objective, less invasive and improved diagnosis of diseases. In this respect, the gold standard for those system include the usage of a optimized representation of the spectral envelope, either based on cepstral coefficients from the mel-scaled Fourier spectral envelope (Mel-Frequency Cepstral Coefficients) or from an all-pole estimation (Linear Prediction Coding Cepstral Coefficients) forcharacterization, and Gaussian Mixture Models for posterior classification. However, the study of recently proposed GMM-based classifiers as well as Nuisance mitigation techniques, such as those employed in speaker recognition, has not been widely considered inpathology detection labours. The present work aims at testing whether or not the employment of such speaker recognition tools might contribute to improve system performance in pathology detection systems, specifically in the automatic detection of Obstructive Sleep Apnea. The testing procedure employs an Obstructive Sleep Apnea database, in conjunction with GMM-based classifiers looking for a better performance. The results show that an improved performance might be obtained by using such approach.

Desarrollo de una herramienta de análisis de la señal de voz

El habla es la principal herramienta de comunicación de la que dispone el ser humano que, no sólo le permite expresar su pensamiento y sus sentimientos sino que le distingue como individuo. El análisis de la señal de voz es fundamental para múltiples aplicaciones como pueden ser: síntesis y reconocimiento de habla, codificación, detección de patologías, identificación y reconocimiento de locutor… En el mercado se pueden encontrar herramientas comerciales o de libre distribución para realizar esta tarea. El objetivo de este Proyecto Fin de Grado es reunir varios algoritmos de análisis de la señal de voz en una única herramienta que se manejará a través de un entorno gráfico. Los algoritmos están siendo utilizados en el Grupo de investigación en Aplicaciones MultiMedia y Acústica de la Universidad Politécnica de Madrid para llevar a cabo su tarea investigadora y para ofertar talleres formativos a los alumnos de grado de la Escuela Técnica Superior de Ingeniería y Sistemas de Telecomunicación. Actualmente se ha encontrado alguna dificultad para poder aplicar los algoritmos ya que se han ido desarrollando a lo largo de varios años, por distintas personas y en distintos entornos de programación. Se han adaptado los programas existentes para generar una única herramienta en MATLAB que permite: . Detección de voz . Detección sordo/sonoro . Extracción y revisión manual de frecuencia fundamental de los sonidos sonoros . Extracción y revisión manual de formantes de los sonidos sonoros En todos los casos el usuario puede ajustar los parámetros de análisis y se ha mantenido y, en algunos casos, ampliado la funcionalidad de los algoritmos existentes. Los resultados del análisis se pueden manejar directamente en la aplicación o guardarse en un fichero. Por último se ha escrito el manual de usuario de la aplicación y se ha generado una aplicación independiente que puede instalarse y ejecutarse aunque no se disponga del software o de la versión adecuada de MATLAB. ABSTRACT. The speech is the main communication tool which has the human that as well as allowing to express his thoughts and feelings distinguishes him as an individual. The analysis of speech signal is essential for multiple applications such as: synthesis and recognition of speech, coding, detection of pathologies, identification and speaker recognition… In the market you can find commercial or open source tools to perform this task. The aim of this Final Degree Project is collect several algorithms of speech signal analysis in a single tool which will be managed through a graphical environment. These algorithms are being used in the research group Aplicaciones MultiMedia y Acústica at the Universidad Politécnica de Madrid to carry out its research work and to offer training workshops for students at the Escuela Técnica Superior de Ingeniería y Sistemas de Telecomunicación. Currently some difficulty has been found to be able to apply the algorithms as they have been developing over several years, by different people and in different programming environments. Existing programs have been adapted to generate a single tool in MATLAB that allows: . Voice Detection . Voice/Unvoice Detection . Extraction and manual review of fundamental frequency of voiced sounds . Extraction and manual review formant voiced sounds In all cases the user can adjust the scan settings, we have maintained and in some cases expanded the functionality of existing algorithms. The analysis results can be managed directly in the application or saved to a file. Finally we have written the application user’s manual and it has generated a standalone application that can be installed and run although the user does not have MATLAB software or the appropriate version.

Cascading appearance-based features for visual voice activity detection

The detection of voice activity is a challenging problem, especially when the level of acoustic noise is high. Most current approaches only utilise the audio signal, making them susceptible to acoustic noise. An obvious approach to overcome this is to use the visual modality. The current state-of-the-art visual feature extraction technique is one that uses a cascade of visual features (i.e. 2D-DCT, feature mean normalisation, interstep LDA). In this paper, we investigate the effectiveness of this technique for the task of visual voice activity detection (VAD), and analyse each stage of the cascade and quantify the relative improvement in performance gained by each successive stage. The experiments were conducted on the CUAVE database and our results highlight that the dynamics of the visual modality can be used to good effect to improve visual voice activity detection performance.

The QUT-NOISE-TIMIT corpus for the evaluation of voice activity detection algorithms

The QUT-NOISE-TIMIT corpus consists of 600 hours of noisy speech sequences designed to enable a thorough evaluation of voice activity detection (VAD) algorithms across a wide variety of common background noise scenarios. In order to construct the final mixed-speech database, a collection of over 10 hours of background noise was conducted across 10 unique locations covering 5 common noise scenarios, to create the QUT-NOISE corpus. This background noise corpus was then mixed with speech events chosen from the TIMIT clean speech corpus over a wide variety of noise lengths, signal-to-noise ratios (SNRs) and active speech proportions to form the mixed-speech QUT-NOISE-TIMIT corpus. The evaluation of five baseline VAD systems on the QUT-NOISE-TIMIT corpus is conducted to validate the data and show that the variety of noise available will allow for better evaluation of VAD systems than existing approaches in the literature.

The delta-phase spectrum with application to voice activity detection and speaker recognition

For several reasons, the Fourier phase domain is less favored than the magnitude domain in signal processing and modeling of speech. To correctly analyze the phase, several factors must be considered and compensated, including the effect of the step size, windowing function and other processing parameters. Building on a review of these factors, this paper investigates a spectral representation based on the Instantaneous Frequency Deviation, but in which the step size between processing frames is used in calculating phase changes, rather than the traditional single sample interval. Reflecting these longer intervals, the term delta-phase spectrum is used to distinguish this from instantaneous derivatives. Experiments show that mel-frequency cepstral coefficients features derived from the delta-phase spectrum (termed Mel-Frequency delta-phase features) can produce broadly similar performance to equivalent magnitude domain features for both voice activity detection and speaker recognition tasks. Further, it is shown that the fusion of the magnitude and phase representations yields performance benefits over either in isolation.

Noise robust voice activity detection using normal probability testing and time-domain histogram analysis

This paper presents a method of voice activity detection (VAD) suitable for high noise scenarios, based on the fusion of two complementary systems. The first system uses a proposed non-Gaussianity score (NGS) feature based on normal probability testing. The second system employs a histogram distance score (HDS) feature that detects changes in the signal through conducting a template-based similarity measure between adjacent frames. The decision outputs by the two systems are then merged using an open-by-reconstruction fusion stage. Accuracy of the proposed method was compared to several baseline VAD methods on a database created using real recordings of a variety of high-noise environments.

Noise robust voice activity detection using features extracted from the time-domain autocorrelation function

This paper presents a method of voice activity detection (VAD) for high noise scenarios, using a noise robust voiced speech detection feature. The developed method is based on the fusion of two systems. The first system utilises the maximum peak of the normalised time-domain autocorrelation function (MaxPeak). The second zone system uses a novel combination of cross-correlation and zero-crossing rate of the normalised autocorrelation to approximate a measure of signal pitch and periodicity (CrossCorr) that is hypothesised to be noise robust. The score outputs by the two systems are then merged using weighted sum fusion to create the proposed autocorrelation zero-crossing rate (AZR) VAD. Accuracy of AZR was compared to state of the art and standardised VAD methods and was shown to outperform the best performing system with an average relative improvement of 24.8% in half-total error rate (HTER) on the QUT-NOISE-TIMIT database created using real recordings from high-noise environments.

Complete-linkage clustering for voice activity detection in audio and visual speech

We propose a novel technique for conducting robust voice activity detection (VAD) in high-noise recordings. We use Gaussian mixture modeling (GMM) to train two generic models; speech and non-speech. We then score smaller segments of a given (unseen) recording against each of these GMMs to obtain two respective likelihood scores for each segment. These scores are used to compute a dissimilarity measure between pairs of segments and to carry out complete-linkage clustering of the segments into speech and non-speech clusters. We compare the accuracy of our method against state-of-the-art and standardised VAD techniques to demonstrate an absolute improvement of 15% in half-total error rate (HTER) over the best performing baseline system and across the QUT-NOISE-TIMIT database. We then apply our approach to the Audio-Visual Database of American English (AVDBAE) to demonstrate the performance of our algorithm in using visual, audio-visual or a proposed fusion of these features.

Improved voice activity detection algorithm using wavelet and support vector machine

This paper proposes an improved voice activity detection (VAD) algorithm using wavelet and support vector machine (SVM) for European Telecommunication Standards Institution (ETS1) adaptive multi-rate (AMR) narrow-band (NB) and wide-band (WB) speech codecs. First, based on the wavelet transform, the original IIR filter bank and pitch/tone detector are implemented, respectively, via the wavelet filter bank and the wavelet-based pitch/tone detection algorithm. The wavelet filter bank can divide input speech signal into several frequency bands so that the signal power level at each sub-band can be calculated. In addition, the background noise level can be estimated in each sub-band by using the wavelet de-noising method. The wavelet filter bank is also derived to detect correlated complex signals like music. Then the proposed algorithm can apply SVM to train an optimized non-linear VAD decision rule involving the sub-band power, noise level, pitch period, tone flag, and complex signals warning flag of input speech signals. By the use of the trained SVM, the proposed VAD algorithm can produce more accurate detection results. Various experimental results carried out from the Aurora speech database with different noise conditions show that the proposed algorithm gives considerable VAD performances superior to the AMR-NB VAD Options 1 and 2, and AMR-WB VAD. (C) 2009 Elsevier Ltd. All rights reserved.

Neurological Disease Detection and Monitoring from Voice Production

The dramatic impact of neurological degenerative pathologies in life quality is a growing concern. It is well known that many neurological diseases leave a fingerprint in voice and speech production. Many techniques have been designed for the detection, diagnose and monitoring the neurological disease. Most of them are costly or difficult to extend to primary attention medical services. Through the present paper it will be shown how some neurological diseases can be traced at the level of phonation. The detection procedure would be based on a simple voice test. The availability of advanced tools and methodologies to monitor the organic pathology of voice would facilitate the implantation of these tests. The paper hypothesizes that some of the underlying mechanisms affecting the production of voice produce measurable correlates in vocal fold biomechanics. A general description of the methodological foundations for the voice analysis system which can estimate correlates to the neurological disease is shown. Some study cases will be presented to illustrate the possibilities of the methodology to monitor neurological diseases by voice

Influence of delay time on regularity estimation for voice pathology detection

The employment of nonlinear analysis techniques for automatic voice pathology detection systems has gained popularity due to the ability of such techniques for dealing with the underlying nonlinear phenomena. On this respect, characterization using nonlinear analysis typically employs the classical Correlation Dimension and the largest Lyapunov Exponent, as well as some regularity quantifiers computing the system predictability. Mostly, regularity features highly depend on a correct choosing of some parameters. One of those, the delay time �, is usually fixed to be 1. Nonetheless, it has been stated that a unity � can not avoid linear correlation of the time series and hence, may not correctly capture system nonlinearities. Therefore, present work studies the influence of the � parameter on the estimation of regularity features. Three � estimations are considered: the baseline value 1; a � based on the Average Automutual Information criterion; and � chosen from the embedding window. Testing results obtained for pathological voice suggest that an improved accuracy might be obtained by using a � value different from 1, as it accounts for the underlying nonlinearities of the voice signal.

A simple but efficient voice activity detection algorithm through Hilbert transform and dynamic threshold for speech pathologies

A simple but efficient voice activity detector based on the Hilbert transform and a dynamic threshold is presented to be used on the pre-processing of audio signals -- The algorithm to define the dynamic threshold is a modification of a convex combination found in literature -- This scheme allows the detection of prosodic and silence segments on a speech in presence of non-ideal conditions like a spectral overlapped noise -- The present work shows preliminary results over a database built with some political speech -- The tests were performed adding artificial noise to natural noises over the audio signals, and some algorithms are compared -- Results will be extrapolated to the field of adaptive filtering on monophonic signals and the analysis of speech pathologies on futures works