Visual Speech Synthesis by Morphing Visemes

We present MikeTalk, a text-to-audiovisual speech synthesizer which converts input text into an audiovisual speech stream. MikeTalk is built using visemes, which are a small set of images spanning a large range of mouth shapes. The visemes are acquired from a recorded visual corpus of a human subject which is specifically designed to elicit one instantiation of each viseme. Using optical flow methods, correspondence from every viseme to every other viseme is computed automatically. By morphing along this correspondence, a smooth transition between viseme images may be generated. A complete visual utterance is constructed by concatenating viseme transitions. Finally, phoneme and timing information extracted from a text-to-speech synthesizer is exploited to determine which viseme transitions to use, and the rate at which the morphing process should occur. In this manner, we are able to synchronize the visual speech stream with the audio speech stream, and hence give the impression of a photorealistic talking face.

Visual Speech Segmentation: Using Facial Cues to Locate Word Boundaries in Continuous Speech

Speech is typically a multimodal phenomenon, yet few studies have focused on the exclusive contributions of visual cues to language acquisition. To address this gap, we investigated whether visual prosodic information can facilitate speech segmentation. Previous research has demonstrated that language learners can use lexical stress and pitch cues to segment speech and that learners can extract this information from talking faces. Thus, we created an artificial speech stream that contained minimal segmentation cues and paired it with two synchronous facial displays in which visual prosody was either informative or uninformative for identifying word boundaries. Across three familiarisation conditions (audio stream alone, facial streams alone, and paired audiovisual), learning occurred only when the facial displays were informative to word boundaries, suggesting that facial cues can help learners solve the early challenges of language acquisition.

Fusion of probabilistic knowledge-based classification rules and learning automata for automatic recognition of digital images

In this paper, the fusion of probabilistic knowledge-based classification rules and learning automata theory is proposed and as a result we present a set of probabilistic classification rules with self-learning capability. The probabilities of the classification rules change dynamically guided by a supervised reinforcement process aimed at obtaining an optimum classification accuracy. This novel classifier is applied to the automatic recognition of digital images corresponding to visual landmarks for the autonomous navigation of an unmanned aerial vehicle (UAV) developed by the authors. The classification accuracy of the proposed classifier and its comparison with well-established pattern recognition methods is finally reported.

Auditory-visual speech integration by prelinguistic infants: Perception of an emergent consonant in the McGurk effect

The McGurk effect, in which auditory [ba] dubbed onto [go] lip movements is perceived as da or tha, was employed in a real-time task to investigate auditory-visual speech perception in prelingual infants. Experiments 1A and 1B established the validity of real-time dubbing for producing the effect. In Experiment 2, 4(1)/(2)-month-olds were tested in a habituation-test paradigm, in which 2 an auditory-visual stimulus was presented contingent upon visual fixation of a live face. The experimental group was habituated to a McGurk stimulus (auditory [ba] visual [ga]), and the control group to matching auditory-visual [ba]. Each group was then presented with three auditory-only test trials, [ba], [da], and [deltaa] (as in then). Visual-fixation durations in test trials showed that the experimental group treated the emergent percept in the McGurk effect, [da] or [deltaa], as familiar (even though they had not heard these sounds previously) and [ba] as novel. For control group infants [da] and [deltaa] were no more familiar than [ba]. These results are consistent with infants'perception of the McGurk effect, and support the conclusion that prelinguistic infants integrate auditory and visual speech information. (C) 2004 Wiley Periodicals, Inc.

Robust indoor speaker recognition in a network of audio and video sensors

Situational awareness is achieved naturally by the human senses of sight and hearing in combination. Automatic scene understanding aims at replicating this human ability using microphones and cameras in cooperation. In this paper, audio and video signals are fused and integrated at different levels of semantic abstractions. We detect and track a speaker who is relatively unconstrained, i.e., free to move indoors within an area larger than the comparable reported work, which is usually limited to round table meetings. The system is relatively simple: consisting of just 4 microphone pairs and a single camera. Results show that the overall multimodal tracker is more reliable than single modality systems, tolerating large occlusions and cross-talk. System evaluation is performed on both single and multi-modality tracking. The performance improvement given by the audio–video integration and fusion is quantified in terms of tracking precision and accuracy as well as speaker diarisation error rate and precision–recall (recognition). Improvements vs. the closest works are evaluated: 56% sound source localisation computational cost over an audio only system, 8% speaker diarisation error rate over an audio only speaker recognition unit and 36% on the precision–recall metric over an audio–video dominant speaker recognition method.

Grammatical priming of visual word recognition in fourth-grade children

Previous work examining context effects in children has been limited to semantic context. The current research examined the effects of grammatical priming of word-naming in fourth-grade children. In Experiment 1, children named both inflected and uninflected noun and verb target words faster when they were preceded by grammatically constraining primes than when they were preceded by neutral primes. Experiment 1 used a long stimulus onset asynchrony (SOA) interval of 750 msec. Experiment 2 replicated the grammatical priming effect at two SOA intervals (400 msec and 700 msec), suggesting that the grammatical priming effect does not reflect the operation of any gross strategic effects directly attributable to the long SOA interval employed in Experiment 1. Grammatical context appears to facilitate target word naming by constraining target word class. Further work is required to elucidate the loci of this effect.

Semantic priming in Alzheimer's dementia: Evidence for dissociation of automatic and attentional processes

The nature of the semantic memory deficit in dementia of the Alzheimer's type (DAT) was investigated in a semantic priming task which was designed to assess both automatic and attention-induced priming effects. Ten DAT patients and 10 age-matched control subjects completed a word naming semantic priming task in which both relatedness proportion (RP) and stimulus-onset asynchrony (SOA) were varied. A clear dissociation between automatic and attentional priming effects in both groups was demonstrated; however, the DAT subjects pattern of priming deviated significantly from that of the normal controls. The DAT patients failed to produce any priming under conditions which encouraged automatic semantic processing and produced facilitation only when the RP was high. In addition, the DAT group produced hyperpriming, with significantly larger facilitation effects than the control group. These results suggest an impairment of automatic spreading activation in DAT and have implications for theories of semantic memory impairment in DAT as well as models of normal priming. (C) 2001 Academic Press.

Methods for automatic and assisted image annotation

Personal memories composed of digital pictures are very popular at the moment. To retrieve these media items annotation is required. During the last years, several approaches have been proposed in order to overcome the image annotation problem. This paper presents our proposals to address this problem. Automatic and semi-automatic learning methods for semantic concepts are presented. The automatic method is based on semantic concepts estimated using visual content, context metadata and audio information. The semi-automatic method is based on results provided by a computer game. The paper describes our proposals and presents their evaluations.

An Interface to Retrieve Personal Memories Using an Iconic Visual Language

Relevant past events can be remembered when visualizing related pictures. The main difficulty is how to find these photos in a large personal collection. Query definition and image annotation are key issues to overcome this problem. The former is relevant due to the diversity of the clues provided by our memory when recovering a past moment and the later because images need to be annotated with information regarding those clues to be retrieved. Consequently, tools to recover past memories should deal carefully with these two tasks. This paper describes a user interface designed to explore pictures from personal memories. Users can query the media collection in several ways and for this reason an iconic visual language to define queries is proposed. Automatic and semi-automatic annotation is also performed using the image content and the audio information obtained when users show their images to others. The paper also presents the user interface evaluation based on tests with 58 participants.

Automatic diagnosis of liver steatosis by ultrasound using autoregressive tissue characterization

Liver steatosis is mainly a textural abnormality of the hepatic parenchyma due to fat accumulation on the hepatic vesicles. Today, the assessment is subjectively performed by visual inspection. Here a classifier based on features extracted from ultrasound (US) images is described for the automatic diagnostic of this phatology. The proposed algorithm estimates the original ultrasound radio-frequency (RF) envelope signal from which the noiseless anatomic information and the textural information encoded in the speckle noise is extracted. The features characterizing the textural information are the coefficients of the first order autoregressive model that describes the speckle field. A binary Bayesian classifier was implemented and the Bayes factor was calculated. The classification has revealed an overall accuracy of 100%. The Bayes factor could be helpful in the graphical display of the quantitative results for diagnosis purposes.

Fatty liver automatic diagnosis from ultrasound images

In this paper an automatic classification algorithm is proposed for the diagnosis of the liver steatosis, also known as, fatty liver, from ultrasound images. The features, automatically extracted from the ultrasound images used by the classifier, are basically the ones used by the physicians in the diagnosis of the disease based on visual inspection of the ultrasound images. The main novelty of the method is the utilization of the speckle noise that corrupts the ultrasound images to compute textural features of the liver parenchyma relevant for the diagnosis. The algorithm uses the Bayesian framework to compute a noiseless image, containing anatomic and echogenic information of the liver and a second image containing only the speckle noise used to compute the textural features. The classification results, with the Bayes classifier using manually classified data as ground truth show that the automatic classifier reaches an accuracy of 95% and a 100% of sensitivity.

Unsupervised automatic music genre classification

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial para obtenção do grau de Mestre em Engenharia Informática

Automatic syllabification for danish text-to-speech systems

In this paper, a rule-based automatic syllabifier for Danish is described using the Maximal Onset Principle. Prior success rates of rule-based methods applied to Portuguese and Catalan syllabification modules were on the basis of this work. The system was implemented and tested using a very small set of rules. The results gave rise to 96.9% and 98.7% of word accuracy rate, contrary to our initial expectations, being Danish a language with a complex syllabic structure and thus difficult to be rule-driven. Comparison with data-driven syllabification system using artificial neural networks showed a higher accuracy rate of the former system.

Statistical pattern recognition for audio-forensics : empirical investigations on the application scenarios audio steganalysis and microphone forensics

Magdeburg, Univ., Fak. für Informatik, Diss., 2013