Recent advances in computer technology and speech and language processing have made possible that some new ways of person-machine communication and computer assistance to human activities start to appear feasible. Concretely, the interest on the development of new challenging applications in indoor environments equipped with multiple multimodal sensors, also known as smart-rooms, has considerably grown. In general, it is well-known that the quality of speech signals captured by microphones that can be located several meters away from the speakers is severely distorted by acoustic noise and room reverberation. In the context of the development of hands-free speech applications in smart-room environments, the use of obtrusive sensors like close-talking microphones is usually not allowed, and consequently, speech technologies must operate on the basis of distant-talking recordings. In such conditions, speech technologies that usually perform reasonably well in free of noise and ...

In many distant speech acquisition scenarios, such as hands-free telephony or teleconferencing, the desired speech signal is corrupted by noise and reverberation. This degrades both the speech quality and intelligibility, making communication difficult or even impossible. Speech enhancement techniques seek to mitigate these effects and extract the desired speech signal. This objective is commonly achieved through the use of microphone arrays, which take advantage of the spatial properties of the sound field in order to reduce noise and reverberation. Spherical microphone arrays, where the microphones are arranged in a spherical configuration, usually mounted on a rigid baffle, are able to analyze the sound field in three dimensions; the captured sound field can then be efficiently described in the spherical harmonic domain (SHD). In this thesis, a number of novel spherical array processing algorithms are proposed, based in the SHD. In ...

Speech, consisting of an auditory and a visual signal, has always been the most important means of communication between humans. It is well known that an optimal conveyance of the message requires that both the auditory and the visual speech signal can be perceived by the receiver. Nowadays people interact countless times with computer systems in every-day situations. Since the ultimate goal is to make this interaction feel completely natural and familiar, the most optimal way to interact with a computer system is by means of speech. Similar to the speech communication between humans, the most appropriate human-machine interaction consists of audiovisual speech signals. In order to allow the computer system to transfer a spoken message towards its users, an audiovisual speech synthesizer is needed to generate novel audiovisual speech signals based on a given text. This dissertation focuses on ...

Speech signals carry important information about a speaker such as age, gender, language, accent and emotional/psychological state. Automatic recognition of speaker characteristics has a wide range of commercial, medical and forensic applications such as interactive voice response systems, service customization, natural human-machine interaction, recognizing the type of pathology of speakers, and directing the forensic investigation process. This research aims to develop accurate methods and tools to identify different physical characteristics of the speakers. Due to the lack of required databases, among all characteristics of speakers, our experiments cover gender recognition, age estimation, language recognition and accent/dialect identification. However, similar approaches and techniques can be applied to identify other characteristics such as emotional/psychological state. For speaker characterization, we first convert variable-duration speech signals into fixed-dimensional vectors suitable for classification/regression algorithms. This is performed by fitting a probability density function to acoustic ...

In many hands-free speech communication applications such as teleconferencing or voice-controlled applications, the recorded microphone signals do not only contain the desired speech signal, but also attenuated and delayed copies of the desired speech signal due to reverberation as well as additive background noise. Reverberation and background noise cause a signal degradation which can impair speech intelligibility and decrease the performance for many signal processing techniques. Acoustic multi-channel equalization techniques, which aim at inverting or reshaping the measured or estimated room impulse responses between the speech source and the microphone array, comprise an attractive approach to speech dereverberation since in theory perfect dereverberation can be achieved. However in practice, such techniques suffer from several drawbacks, such as uncontrolled perceptual effects, sensitivity to perturbations in the measured or estimated room impulse responses, and background noise amplification. The aim of this thesis ...

Determining the geometry of an acoustic enclosure using microphone arrays has become an active area of research. Knowledge gained about the acoustic environment, such as the location of reflectors, can be advantageous for applications such as sound source localization, dereverberation and adaptive echo cancellation by assisting in tracking environment changes and helping the initialization of such algorithms. A methodology to blindly infer the geometry of an acoustic enclosure by estimating the location of reflective surfaces based on acoustic measurements using an arbitrary array geometry is developed and analyzed. The starting point of this work considers a geometric constraint, valid both in two and three-dimensions, that converts time-of-arrival and time-difference-of-arrival information into elliptical constraints about the location of reflectors. Multiple constraints are combined to yield the line or plane parameters of the reflectors by minimizing a specific cost function in the ...

In typical speech communication applications, such as hands-free mobile telephony, voice-controlled systems and hearing aids, the recorded microphone signals are corrupted by background noise, room reverberation and far-end echo signals. This signal degradation can lead to total unintelligibility of the speech signal and decreases the performance of automatic speech recognition systems. In this thesis several multi-microphone noise reduction and dereverberation techniques are developed. In Part I we present a Generalised Singular Value Decomposition (GSVD) based optimal filtering technique for enhancing multi-microphone speech signals which are degraded by additive coloured noise. Several techniques are presented for reducing the computational complexity and we show that the GSVD-based optimal filtering technique can be integrated into a `Generalised Sidelobe Canceller' type structure. Simulations show that the GSVD-based optimal filtering technique achieves a larger signal-to-noise ratio improvement than standard fixed and adaptive beamforming techniques and ...

The problem of segregating a sound source of interest from an acoustic background has been extensively studied due to applications in hearing prostheses, robust speech/speaker recognition and audio information retrieval. Computational auditory scene analysis (CASA) approaches the segregation problem by utilizing grouping cues involved in the perceptual organization of sound by human listeners. Binaural processing, where input signals resemble those that enter the two ears, is of particular interest in the CASA field. The dominant approach to binaural segregation has been to derive spatially selective filters in order to enhance the signal in a direction of interest. As such, the problems of sound localization and sound segregation are closely tied. While spatial filtering has been widely utilized, substantial performance degradation is incurred in reverberant environments and more fundamentally, segregation cannot be performed without sufficient spatial separation between sources. This dissertation ...

In the world of Information and communications technology (ICT), strategies for innovation and development are increasingly focusing on applications that require spatial representation and real-time interaction with and within 3D-media environments. One of the major challenges that such applications have to address is user-centricity, reflecting e.g. on developing complexity-hiding services so that people can personalize their own delivery of services. In these terms, multimodal interfaces represent a key factor for enabling an inclusive use of new technologies by everyone. In order to achieve this, multimodal realistic models that describe our environment are needed, and in particular models that accurately describe the acoustics of the environment and communication through the auditory modality are required. Examples of currently active research directions and application areas include 3DTV and future internet, 3D visual-sound scene coding, transmission and reconstruction and teleconferencing systems, to name but ...

Current Human-Machine Interfaces (HMI) lack of “emotional intelligence”, i.e. they are not able to identify human emotional states and take this information into account to decide on the proper actions to execute. The goal of affective computing is to fill this lack by detecting emotional cues occurring during Human-Computer Interaction (HCI) and synthesizing emotional responses. In the last decades, most of the studies on emotion assessment have focused on the analysis of facial expressions and speech to determine the emotional state of a person. Physiological activity also includes emotional information that can be used for emotion assessment but has received less attention despite of its advantages (for instance it can be less easily faked than facial expressions). This thesis reports on the use of two types of physiological activities to assess emotions in the context of affective computing: the activity ...

The research in this thesis addresses the problem of automatic speech recognition in noisy environments. Automatic speech recognition systems obtain acceptable performances in noise free conditions but these performances degrade dramatically in presence of additive noise. This is mainly due to the mismatch between the training and the noisy operating conditions. In the time-frequency representation of the noisy speech signal, some of the clean speech features are masked by noise. In this case the clean speech features cannot be correctly estimated from the noisy speech and therefore they are considered as missing or unreliable. In order to improve the performance of speech recognition systems in additive noise conditions, special attention should be paid to the problems of detection and compensation of these unreliable features. This thesis is concerned with the problem of missing features applied to automatic speaker-independent speech recognition. ...

Recently emerging techniques like wave field synthesis (WFS) or Higher-Order Ambisonics (HOA) allow for high-quality spatial audio reproduction, which makes them candidates for the audio reproduction in future telepresence systems or interactive gaming environments with acoustic human-machine interfaces. In such scenarios, acoustic echo cancellation (AEC) will generally be necessary to remove the loudspeaker echoes in the recorded microphone signals before further processing. Moreover, the reproduction quality of WFS or HOA can be improved by adaptive pre-equalization of the loudspeaker signals, as facilitated by listening room equalization (LRE). However, AEC and LRE require adaptive filters, where the large number of reproduction channels of WFS and HOA imply major computational and algorithmic challenges for the implementation of adaptive filters. A technique called wave-domain adaptive filtering (WDAF) promises to master these challenges. However, known literature is still far away from providing sufficient insight ...

This dissertation studies soft biometrics traits, their applicability in different security and commercial scenarios, as well as related usability aspects. We place the emphasis on human facial soft biometric traits which constitute the set of physical, adhered or behavioral human characteristics that can partially differentiate, classify and identify humans. Such traits, which include characteristics like age, gender, skin and eye color, the presence of glasses, moustache or beard, inherit several advantages such as ease of acquisition, as well as a natural compatibility with how humans perceive their surroundings. Specifically, soft biometric traits are compatible with the human process of classifying and recalling our environment, a process which involves constructions of hierarchical structures of different refined traits. This thesis explores these traits, and their application in soft biometric systems (SBSs), and specifically focuses on how such systems can achieve different goals ...

Automatic speaker recognition is the use of a machine to identify an individual from a spoken sentence. Recently, this technology has been undergone an increasing use in applications such as access control, transaction authentication, law enforcement, forensics, and system customisation, among others. One of the central questions addressed by this field is what is it in the speech signal that conveys speaker identity. Traditionally, automatic speaker recognition systems have relied mostly on short-term features related to the spectrum of the voice. However, human speaker recognition relies on other sources of information; therefore, there is reason to believe that these sources can play also an important role in the automatic speaker recognition task, adding complementary knowledge to the traditional spectrum-based recognition systems and thus improving their accuracy. The main objective of this thesis is to add prosodic information to a traditional ...

The interest in the field of speech enhancement emerges from the increased usage of digital speech processing applications like mobile telephony, digital hearing aids and human-machine communication systems in our daily life. The trend to make these applications mobile increases the variety of potential sources for quality degradation. Speech enhancement methods can be used to increase the quality of these speech processing devices and make them more robust under noisy conditions. The name "speech enhancement" refers to a large group of methods that are all meant to improve certain quality aspects of these devices. Examples of speech enhancement algorithms are echo control, bandwidth extension, packet loss concealment and noise reduction. In this thesis we focus on single-microphone additive noise reduction and aim at methods that work in the discrete Fourier transform (DFT) domain. The main objective of the presented research ...