Audiovisual Speech Processing

This book presents a complete overview of all aspects of audiovisual speech including perception, production, brain processing and technology.

Perceptual processes mediating recognition, including the recognition of objects and spoken words, is inherently multisensory. This is true in spite of the fact that sensory inputs are segregated in early stages of neuro-sensory encoding. In face-to-face communication, for example, auditory information is processed in the cochlea, encoded in auditory sensory nerve, and processed in lower cortical areas. Eventually, these “sounds” are processed in higher cortical pathways such as the auditory cortex where it is perceived as speech. Likewise, visual information obtained from observing a talker’s articulators is encoded in lower visual pathways. Subsequently, this information undergoes processing in the visual cortex prior to the extraction of articulatory gestures in higher cortical areas associated with speech and language. As language perception unfolds, information garnered from visual articulators interacts with language processing in multiple brain regions. This occurs via visual projections to auditory, language, and multisensory brain regions. The association of auditory and visual speech signals makes the speech signal a highly “configural” percept. An important direction for the field is thus to provide ways to measure the extent to which visual speech information influences auditory processing, and likewise, assess how the unisensory components of the signal combine to form a configural/integrated percept. Numerous behavioral measures such as accuracy (e.g., percent correct, susceptibility to the “McGurk Effect”) and reaction time (RT) have been employed to assess multisensory integration ability in speech perception. On the other hand, neural based measures such as fMRI, EEG and MEG have been employed to examine the locus and or time-course of integration. The purpose of this Research Topic is to find converging behavioral and neural based assessments of audiovisual integration in speech perception. A further aim is to investigate speech recognition ability in normal hearing, hearing-impaired, and aging populations. As such, the purpose is to obtain neural measures from EEG as well as fMRI that shed light on the neural bases of multisensory processes, while connecting them to model based measures of reaction time and accuracy in the behavioral domain. In doing so, we endeavor to gain a more thorough description of the neural bases and mechanisms underlying integration in higher order processes such as speech and language recognition.

This book presents a summary of the cognitively inspired basis behind multimodal speech enhancement, covering the relationship between audio and visual modalities in speech, as well as recent research into audiovisual speech correlation. A number of audiovisual speech filtering approaches that make use of this relationship are also discussed. A novel multimodal speech enhancement system, making use of both visual and audio information to filter speech, is presented, and this book explores the extension of this system with the use of fuzzy logic to demonstrate an initial implementation of an autonomous, adaptive, and context aware multimodal system. This work also discusses the challenges presented with regard to testing such a system, the limitations with many current audiovisual speech corpora, and discusses a suitable approach towards development of a corpus designed to test this novel, cognitively inspired, speech filtering system.

Speech processing addresses various scientific and technologicalareas. It includes speech analysis and variable rate coding, inorder to store or transmit speech. It also covers speech synthesis,especially from text, speech recognition, including speaker andlanguage identification, and spoken language understanding. This book covers the following topics: how to realize speechproduction and perception systems, how to synthesize and understandspeech using state-of-the-art methods in signal processing, patternrecognition, stochastic modelling computational linguistics andhuman factor studies.

Automatic speech recognition suffers from a lack of robustness with respect to noise, reverberation and interfering speech. The growing field of speech recognition in the presence of missing or uncertain input data seeks to ameliorate those problems by using not only a preprocessed speech signal but also an estimate of its reliability to selectively focus on those segments and features that are most reliable for recognition. This book presents the state of the art in recognition in the presence of uncertainty, offering examples that utilize uncertainty information for noise robustness, reverberation robustness, simultaneous recognition of multiple speech signals, and audiovisual speech recognition. The book is appropriate for scientists and researchers in the field of speech recognition who will find an overview of the state of the art in robust speech recognition, professionals working in speech recognition who will find strategies for improving recognition results in various conditions of mismatch, and lecturers of advanced courses on speech processing or speech recognition who will find a reference and a comprehensive introduction to the field. The book assumes an understanding of the fundamentals of speech recognition using Hidden Markov Models.

Auditory and visual speech recognition unfolds in real time and occurs effortlessly for normal hearing listeners. However, model theoretic descriptions of the systems level cognitive processes responsible for integrating auditory and visual speech information are currently lacking, primarily because they rely too heavily on accuracy rather than reaction time predictions. Speech and language researchers have argued about whether audiovisual integration occurs in a parallel or in coactive fashion, and also the extent to which audiovisual occurs in an efficient manner. The Double Factorial Paradigm introduced in Section 1 is an experimental paradigm that is equipped to address dynamical processing issues related to architecture (parallel vs. coactive processing) as well as efficiency (capacity). Experiment 1 employed a simple word discrimination task to assess both architecture and capacity in high accuracy settings. Experiments 2 and 3 assessed these same issues using auditory and visual distractors in Divided Attention and Focused Attention tasks respectively. Experiment 4 investigated audiovisual integration efficiency across different auditory signal-to-noise ratios. The results can be summarized as follows: Integration typically occurs in parallel with an efficient stopping rule, integration occurs automatically in both focused and divided attention versions of the task, and audiovisual integration is only efficient (in the time domain) when the clarity of the auditory signal is relatively poor--although considerable individual differences were observed. In Section 3, these results were captured within the milieu of parallel linear dynamic processing models with cross channel interactions. Finally, in Section 4, I discussed broader implications for this research, including applications for clinical research and neural-biological models of audiovisual convergence.

Real World Speech Processing brings together in one place important contributions and up-to-date research results in this fast-moving area. The contributors to this work were selected from the leading researchers and practitioners in this field. The work, originally published as Volume 36, Numbers 2-3 of the Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, will be valuable to anyone working or researching in the field of speech processing. It serves as an excellent reference, providing insight into some of the most challenging issues being examined today.

Automatic speech recognition suffers from a lack of robustness with respect to noise, reverberation and interfering speech. The growing field of speech recognition in the presence of missing or uncertain input data seeks to ameliorate those problems by using not only a preprocessed speech signal but also an estimate of its reliability to selectively focus on those segments and features that are most reliable for recognition. This book presents the state of the art in recognition in the presence of uncertainty, offering examples that utilize uncertainty information for noise robustness, reverberation robustness, simultaneous recognition of multiple speech signals, and audiovisual speech recognition. The book is appropriate for scientists and researchers in the field of speech recognition who will find an overview of the state of the art in robust speech recognition, professionals working in speech recognition who will find strategies for improving recognition results in various conditions of mismatch, and lecturers of advanced courses on speech processing or speech recognition who will find a reference and a comprehensive introduction to the field. The book assumes an understanding of the fundamentals of speech recognition using Hidden Markov Models.