Visual Speech Cues Research Articles

Visual speech form influences the speed of auditory speech processing

An important property of visual speech (movements of the lips and mouth) is that it generally begins before auditory speech. Research using brain-based paradigms has demonstrated that seeing visual speech speeds up the activation of the listener’s auditory cortex but it is not clear whether these observed neural processes link to behaviour. It was hypothesized that the very early portion of visual speech (occurring before auditory speech) will allow listeners to predict the following auditory event and so facilitate the speed of speech perception. This was tested in the current behavioural experiments. Further, we tested whether the salience of the visual speech played a role in this speech facilitation effect (Experiment 1). We also determined the relative contributions that visual form (what) and temporal (when) cues made (Experiment 2). The results showed that visual speech cues facilitated response times and that this was based on form rather than temporal cues.

Erratum: Neural entrainment to rhythmically-presented auditory, visual and audio-visual speech in children

[This corrects the article on p. 216 in vol. 3, PMID: 22833726.].

Brain responses and looking behavior during audiovisual speech integration in infants predict auditory speech comprehension in the second year of life

The use of visual cues during the processing of audiovisual (AV) speech is known to be less efficient in children and adults with language difficulties and difficulties are known to be more prevalent in children from low-income populations. In the present study, we followed an economically diverse group of thirty-seven infants longitudinally from 6–9 months to 14–16 months of age. We used eye-tracking to examine whether individual differences in visual attention during AV processing of speech in 6–9 month old infants, particularly when processing congruent and incongruent auditory and visual speech cues, might be indicative of their later language development. Twenty-two of these 6–9 month old infants also participated in an event-related potential (ERP) AV task within the same experimental session. Language development was then followed-up at the age of 14–16 months, using two measures of language development, the Preschool Language Scale and the Oxford Communicative Development Inventory. The results show that those infants who were less efficient in auditory speech processing at the age of 6–9 months had lower receptive language scores at 14–16 months. A correlational analysis revealed that the pattern of face scanning and ERP responses to audiovisually incongruent stimuli at 6–9 months were both significantly associated with language development at 14–16 months. These findings add to the understanding of individual differences in neural signatures of AV processing and associated looking behavior in infants.

Audiovisuelle Sprechererkennung durch linguistisch naive Personen

Human speech perception is not only based on acoustic speech signals but also on visual cues like lip or jaw movements. Based on this assumption we used a between-subject design to test listeners’ speaker identification ability in a voice line-up after they were familiarized with a speaker under either of the following condition: (a) visual and degraded acoustic information, (b) degraded acoustic information only, and (c) visual information only. The results from this experiment indicate that listeners are able to perform the identification task to a considerable degree under all three experimental conditions. We conclude that listeners’ identification ability of speakers based on degraded acoustic material is about as good as their identification ability based on visual speech cues. The combination of acoustic and visual cues does not enhance listeners’ performance.

Age-related sensitive periods influence visual language discrimination in adults

Adults as well as infants have the capacity to discriminate languages based on visual speech alone. Here, we investigated whether adults' ability to discriminate languages based on visual speech cues is influenced by the age of language acquisition. Adult participants who had all learned English (as a first or second language) but did not speak French were shown faces of bilingual (French/English) speakers silently reciting sentences in either language. Using only visual speech information, adults who had learned English from birth or as a second language before the age of 6 could discriminate between French and English significantly better than chance. However, adults who had learned English as a second language after age 6 failed to discriminate these two languages, suggesting that early childhood exposure is crucial for using relevant visual speech information to separate languages visually. These findings raise the possibility that lowered sensitivity to non-native visual speech cues may contribute to the difficulties encountered when learning a new language in adulthood.

Assessing spoken word recognition in children who are deaf or hard of hearing: a translational approach.

Under natural conditions, listeners use both auditory and visual speech cues to extract meaning from speech signals containing many sources of variability. However, traditional clinical tests of spoken word recognition routinely employ isolated words or sentences produced by a single talker in an auditory-only presentation format. The more central cognitive processes used during multimodal integration, perceptual normalization, and lexical discrimination that may contribute to individual variation in spoken word recognition performance are not assessed in conventional tests of this kind. In this article, we review our past and current research activities aimed at developing a series of new assessment tools designed to evaluate spoken word recognition in children who are deaf or hard of hearing. These measures are theoretically motivated by a current model of spoken word recognition and also incorporate "real-world" stimulus variability in the form of multiple talkers and presentation formats. The goal of this research is to enhance our ability to estimate real-world listening skills and to predict benefit from sensory aid use in children with varying degrees of hearing loss.

Short and sweet, or long and complex? Perceiving temporal synchrony in audiovisual events

Perceived synchrony varies depending on the audiovisual event. Typically, asynchrony is tolerated at greater lead- and lag-times for speech and music than for action events. The tolerance for asynchrony in speech has been attributed to the unity assumption, which proposes a bonding of auditory and visual speech cues through associations in several dimensions. However, the variations in synchrony perception for different audiovisual events may simply be related to their complexity; where speech and music fluctuate naturally, actions involve isolated events and anticipated moments of impact. The current study measured perception of synchrony for long (13 s) and short (1 s) variants of three types of stimuli: (1) action, represented by a game of chess, (2) music, played by a drummer and (3) speech, presented by an anchorwoman in a newscast. The long variants allowed events to play out with their natural dynamics, whereas short variants offered controlled and predictable single actions or events, selected from the longer segments. Results show that among the long stimuli, lead asynchrony was detected sooner for speech than for chess. This contrasts both with previous research and our own predictions, although it may be related to characteristics of the selected chess scene. Interestingly, tolerance to asynchrony was generally greater for short, than for long, stimuli, especially for speech. These findings suggest that the dynamics of complex events cannot account for previously observed differences in synchrony perception between speech and action events.

Neural entrainment to rhythmically presented auditory, visual, and audio-visual speech in children.

Auditory cortical oscillations have been proposed to play an important role in speech perception. It is suggested that the brain may take temporal “samples” of information from the speech stream at different rates, phase resetting ongoing oscillations so that they are aligned with similar frequency bands in the input (“phase locking”). Information from these frequency bands is then bound together for speech perception. To date, there are no explorations of neural phase locking and entrainment to speech input in children. However, it is clear from studies of language acquisition that infants use both visual speech information and auditory speech information in learning. In order to study neural entrainment to speech in typically developing children, we use a rhythmic entrainment paradigm (underlying 2 Hz or delta rate) based on repetition of the syllable “ba,” presented in either the auditory modality alone, the visual modality alone, or as auditory-visual speech (via a “talking head”). To ensure attention to the task, children aged 13 years were asked to press a button as fast as possible when the “ba” stimulus violated the rhythm for each stream type. Rhythmic violation depended on delaying the occurrence of a “ba” in the isochronous stream. Neural entrainment was demonstrated for all stream types, and individual differences in standardized measures of language processing were related to auditory entrainment at the theta rate. Further, there was significant modulation of the preferred phase of auditory entrainment in the theta band when visual speech cues were present, indicating cross-modal phase resetting. The rhythmic entrainment paradigm developed here offers a method for exploring individual differences in oscillatory phase locking during development. In particular, a method for assessing neural entrainment and cross-modal phase resetting would be useful for exploring developmental learning difficulties thought to involve temporal sampling, such as dyslexia.

Updating expectencies about audiovisual associations in speech

The processing of multisensory information depends on the learned association between sensory cues. In the case of speech there is a well-learned association between the movements of the lips and the subsequent sound. That is, particular lip and mouth movements reliably lead to a specific sound. EEG and MEG studies that have investigated the differences between this ‘congruent’ AV association and other ‘incongruent’ associations have commonly reported ERP differences from 350 ms after sound onset. Using a 256 active electrode EEG system, we tested whether this ‘congruency effect’ would be reduced in the context where most of the trials had an altered audiovisual association (auditory speech paired with mismatched visual lip movements). Participants were presented stimuli over 2 sessions: in one session only 15% were incongruent trials; in the other session, 85% were incongruent trials. We found a congruency effect, showing differences in ERP between congruent and incongruent speech between 350 and 500 ms. Importantly, this effect was reduced within the context of mostly incongruent trials. This reduction in the congruency effect indicates that the way in which AV speech is processed depends on the context it is viewed in. Furthermore, this result suggests that exposure to novel sensory relationships leads to updated expectations regarding the relationship between auditory and visual speech cues.

Speak, memory—Wherefore art thou, invariance?

Spoken language is highly variable, reflecting factors of environmental (e.g., acoustic-background noise, reverberation), linguistic (e.g., speaking-style), and idiosyncratic (e.g., voice-quality) origin. Despite such variability, listeners rarely experience difficulty understanding speech. What brain mechanisms underlie this perceptual resilience, and where does the invariance reside (if anywhere) that enables the signal to be reliably decoded and understood? A theoretical framework—DejaNets—is described for how the brain may go from “sound to meaning.” Key is speech representations in memory, crucial for the parsing, analysis, and interpretation of sensory signals. The acoustic waveform is viewed as inherently ambiguous, its interpretation dependent on combining data streams, some sensory (e.g., visual-speech cues), others internal, derived from memory and knowledge schema. This interpretative process is mediated by a hierarchical network of neural oscillators spanning a broad range of time constants (ca. 15–2 000 ms), consistent with the time course and temporal structure of spoken language. They reflect data-fetching, parsing, and pattern-matching involved in decoding and interpreting the speech signal. DejaNets accounts for many (otherwise) paradoxical and mysterious properties of spoken language including categorical perception, the McGurk effect, phonemic restoration, semantic context, and robustness/sensitivity to variation in pronunciation, speaking rate and the ambient acoustic environment. [Work supported by AFOSR.]

Does audiovisual speech offer a fountain of youth for old ears? An event-related brain potential study of age differences in audiovisual speech perception.

The current study addressed the question whether audiovisual (AV) speech can improve speech perception in older and younger adults in a noisy environment. Event-related potentials (ERPs) were recorded to investigate age-related differences in the processes underlying AV speech perception. Participants performed an object categorization task in three conditions, namely auditory-only (A), visual-only (V), and AVspeech. Both age groups revealed an equivalent behavioral AVspeech benefit over unisensory trials. ERP analyses revealed an amplitude reduction of the auditory P1 and N1 on AVspeech trials relative to the summed unisensory (A + V) response in both age groups. These amplitude reductions are interpreted as an indication of multisensory efficiency as fewer neural resources were recruited to achieve better performance. Of interest, the observed P1 amplitude reduction was larger in older adults. Younger and older adults also showed an earlier auditory N1 in AVspeech relative to A and A + V trials, an effect that was again greater in the older adults. The degree of multisensory latency shift was predicted by basic auditory functioning (i.e., higher hearing thresholds were associated with larger latency shifts) in both age groups. Together, the results show that AV speech processing is not only intact in older adults, but that the facilitation of neural responses occurs earlier in and to a greater extent than in younger adults. Thus, older adults appear to benefit more from additional visual speech cues than younger adults, possibly to compensate for more impoverished unisensory inputs because of sensory aging.

The effects of blurred vision on auditory-visual speech perception in younger and older adults

Speech understanding is improved when the observer can both see and hear the talker. This study compared the effects of reduced visual acuity on auditory-visual (AV) speech-recognition in noise among younger and older adults. Two groups of participants performed a closed-set sentence-recognition task in one auditory-alone (A-alone) condition and under three AV conditions: normal visual acuity (6/6), and with blurred vision to simulate a 6/30 and 6/60 visual impairment. The results showed that (1) the addition of visual speech cues improved speech-perception relative to the A-alone condition, (2) under the AV conditions, performance declined as the amount of blurring increased, (3) even under the AV condition that simulated a visual acuity of 6/60, the speech recognition scores were significantly higher than those obtained under the A-alone condition, and (4) generally, younger adults obtained higher scores than older adults under all conditions. Our results demonstrate the benefits of visual cues to enhance speech understanding even when visual acuity is not optimal.SumarioLa comprensión del lenguaje mejora cuando el observador puede tanto ver como oír a su interlocutor. Este estudio compara los efectos de una agudeza visual reducida, en el reconocimiento auditivo-visual (AV) del lenguaje con ruido, entre adultos jóvenes y mayores. Dos grupos de participantes realizaron una tarea de reconocimiento de oraciones en contexto cerrado en una condición solo auditiva (Solo-A) y en tres condiciones AV: con agudeza visual normal (6/6) y con visión borrosa simulando impedimentos visuales de 6/30 y 6/60. Los resultados mostraron: (1) la adición de claves visuales de lenguaje mejora la percepción del mismo en relación con la condición de Solo-A; (2) en las condiciones AV, el desempeño declinó conforme aumentó el grado de visión borrosa; (3) incluso en la condición AV que simulaba una agudeza visual de 6/60, las puntuaciones en el reconocimiento del lenguaje fueron significativamente superiores que las obtenidas en la condición de Solo-A y (4) generalmente, los adultos jóvenes obtuvieron puntuaciones más altas que los adultos mayores, en todas las condiciones. Nuestros resultados demuestran los beneficios de las claves visuales para aumentar la comprensión del lenguaje, incluso cuando la agudeza visual no es óptima.

Visual phonetic processing localized using speech and nonspeech face gestures in video and point‐light displays

The talking face affords multiple types of information. To isolate cortical sites with responsibility for integrating linguistically relevant visual speech cues, speech and nonspeech face gestures were presented in natural video and point-light displays during fMRI scanning at 3.0T. Participants with normal hearing viewed the stimuli and also viewed localizers for the fusiform face area (FFA), the lateral occipital complex (LOC), and the visual motion (V5/MT) regions of interest (ROIs). The FFA, the LOC, and V5/MT were significantly less activated for speech relative to nonspeech and control stimuli. Distinct activation of the posterior superior temporal sulcus and the adjacent middle temporal gyrus to speech, independent of media, was obtained in group analyses. Individual analyses showed that speech and nonspeech stimuli were associated with adjacent but different activations, with the speech activations more anterior. We suggest that the speech activation area is the temporal visual speech area (TVSA), and that it can be localized with the combination of stimuli used in this study.

The role of speech production system in audiovisual speech perception.

Seeing the articulatory gestures of the speaker significantly enhances speech perception. Findings from recent neuroimaging studies suggest that activation of the speech motor system during lipreading enhance speech perception by tuning, in a top-down fashion, speech-sound processing in the superior aspects of the posterior temporal lobe. Anatomically, the superior-posterior temporal lobe areas receive connections from the auditory, visual, and speech motor cortical areas. Thus, it is possible that neuronal receptive fields are shaped during development to respond to speech-sound features that coincide with visual and motor speech cues, in contrast with the anterior/lateral temporal lobe areas that might process speech sounds predominantly based on acoustic cues. The superior-posterior temporal lobe areas have also been consistently associated with auditory spatial processing. Thus, the involvement of these areas in audiovisual speech perception might partly be explained by the spatial processing requirements when associating sounds, seen articulations, and one’s own motor movements. Tentatively, it is possible that the anterior “what” and posterior “where / how” auditory cortical processing pathways are parts of an interacting network, the instantaneous state of which determines what one ultimately perceives, as potentially reflected in the dynamics of oscillatory activity.

Audio-Visual Speech Cue Combination

BackgroundDifferent sources of sensory information can interact, often shaping what we think we have seen or heard. This can enhance the precision of perceptual decisions relative to those made on the basis of a single source of information. From a computational perspective, there are multiple reasons why this might happen, and each predicts a different degree of enhanced precision. Relatively slight improvements can arise when perceptual decisions are made on the basis of multiple independent sensory estimates, as opposed to just one. These improvements can arise as a consequence of probability summation. Greater improvements can occur if two initially independent estimates are summated to form a single integrated code, especially if the summation is weighted in accordance with the variance associated with each independent estimate. This form of combination is often described as a Bayesian maximum likelihood estimate. Still greater improvements are possible if the two sources of information are encoded via a common physiological process.Principal FindingsHere we show that the provision of simultaneous audio and visual speech cues can result in substantial sensitivity improvements, relative to single sensory modality based decisions. The magnitude of the improvements is greater than can be predicted on the basis of either a Bayesian maximum likelihood estimate or a probability summation.ConclusionOur data suggest that primary estimates of speech content are determined by a physiological process that takes input from both visual and auditory processing, resulting in greater sensitivity than would be possible if initially independent audio and visual estimates were formed and then subsequently combined.

Speech identification in noise: Contribution of temporal, spectral, and visual speech cues

This study investigated the degree to which two types of reduced auditory signals (cochlear implant simulations) and visual speech cues combined for speech identification. The auditory speech stimuli were filtered to have only amplitude envelope cues or both amplitude envelope and spectral cues and were presented with/without visual speech. In Experiment 1, IEEE sentences were presented in quiet and noise. For in-quiet presentation, speech identification was enhanced by the addition of both spectral and visual speech cues. Due to a ceiling effect, the degree to which these effects combined could not be determined. In noise, these facilitation effects were more marked and were additive. Experiment 2 examined consonant and vowel identification in the context of CVC or VCV syllables presented in noise. For consonants, both spectral and visual speech cues facilitated identification and these effects were additive. For vowels, the effect of combined cues was underadditive, with the effect of spectral cues reduced when presented with visual speech cues. Analysis indicated that without visual speech, spectral cues facilitated the transmission of place information and vowel height, whereas with visual speech, they facilitated lip rounding, with little impact on the transmission of place information.

Evaluating the Effort Expended to Understand Speech in Noise Using a Dual-Task Paradigm: The Effects of Providing Visual Speech Cues

Using a dual-task paradigm, 2 experiments (Experiments 1 and 2) were conducted to assess differences in the amount of listening effort expended to understand speech in noise in audiovisual (AV) and audio-only (A-only) modalities. Experiment 1 had equivalent noise levels in both modalities, and Experiment 2 equated speech recognition performance levels by increasing the noise in the AV versus A-only modality. Sixty adults were randomly assigned to Experiment 1 or Experiment 2. Participants performed speech and tactile recognition tasks separately (single task) and concurrently (dual task). The speech tasks were performed in both modalities. Accuracy and reaction time data were collected as well as ratings of perceived accuracy and effort. In Experiment 1, the AV modality speech recognition was rated as less effortful, and accuracy scores were higher than A only. In Experiment 2, reaction times were slower, tactile task performance was poorer, and listening effort increased, in the AV versus the A-only modality. At equivalent noise levels, speech recognition performance was enhanced and subjectively less effortful in the AV than A-only modality. At equivalent accuracy levels, the dual-task performance decrements (for both tasks) suggest that the noisier AV modality was more effortful than the A-only modality.

Electrophysiological evidence of illusory audiovisual speech percept in human infants

How effortlessly and quickly infants acquire their native language remains one of the most intriguing questions of human development. Our study extends this question into the audiovisual domain, taking into consideration visual speech cues, which were recently shown to have more importance for young infants than previously anticipated [Weikum WM, Vouloumanos A, Navarra J, Soto-Faraco S, Sebastián-Gallés N, Werker JF (2007) Science 316:1159]. A particularly interesting phenomenon of audiovisual speech perception is the McGurk effect [McGurk H, MacDonald J (1976) Nature 264:746-748], an illusory speech percept resulting from integration of incongruent auditory and visual speech cues. For some phonemes, the human brain does not detect the mismatch between conflicting auditory and visual cues but automatically assimilates them into the closest legal phoneme, sometimes different from both auditory and visual ones. Measuring event-related brain potentials in 5-month-old infants, we demonstrate differential brain responses when conflicting auditory and visual speech cues can be integrated and when they cannot be fused into a single percept. This finding reveals a surprisingly early ability to perceive speech cross-modally and highlights the role of visual speech experience during early postnatal development in learning of the phonemes and phonotactics of the native language.

Frequency-band importance functions for auditory and auditory-visual speech by hearing-impaired adults

How we listen to speech appears to be fundamentally different in a number of respects when we can simultaneously see the face of the speaker while listening to his or her speech. Not only is our ability to recognize and understand speech far better when we can see as well as hear, as compared to hearing alone, but the way we hear is also different. This is evident in the patterns of activity in primary auditory cortex, which are different for auditory versus auditory-visual speech inputs, as well as data from normal-hearing subjects suggesting that auditory attention is focused on different spectral regions depending on whether visual speech cues are available. The present study examines whether frequency band-importance functions are different for auditory and auditory-visual speech recognition in a group of hearing-impaired listeners. Results show that hearing-impaired listeners perform much like normal-hearing subjects in attending to primarily low-frequency speech cues under auditory-visual conditions. In contrast, under auditory-alone conditions, hearing-impaired listeners place more importance on mid-to-high-frequency acoustic information, presumably to better recognize place of articulation cues.

Frequency band-importance functions for auditory and auditory-visual speech recognition

In many everyday listening environments, speech communication involves the integration of both acoustic and visual speech cues. This is especially true in noisy and reverberant environments where the speech signal is highly degraded, or when the listener has a hearing impairment. Understanding the mechanisms involved in auditory-visual integration is a primary interest of this work. Of particular interest is whether listeners are able to allocate their attention to various frequency regions of the speech signal differently under auditory-visual conditions and auditory-alone conditions. For auditory speech recognition, the most important frequency regions tend to be around 1500–3000 Hz, corresponding roughly to important acoustic cues for place of articulation. The purpose of this study is to determine the most important frequency region under auditory-visual speech conditions. Frequency band-importance functions for auditory and auditory-visual conditions were obtained by having subjects identify speech tokens under conditions where the speech-to-noise ratio of different parts of the speech spectrum is independently and randomly varied on every trial. Point biserial correlations were computed for each separate spectral region and the normalized correlations are interpreted as weights indicating the importance of each region. Relations among frequency-importance functions for auditory and auditory-visual conditions will be discussed.