Alexandra Jesse

Positional effects in the lexical retuning of speech perception

Listeners use lexical knowledge to adjust to speakers’ idiosyncratic pronunciations. Dutch listeners learn to interpret an ambiguous sound between /s/ and /f/ as /f/ if they hear it word-finally in Dutch words normally ending in /f/, but as /s/ if they hear it in normally /s/-final words. Here, we examined two positional effects in lexically guided retuning. In Experiment 1, ambiguous sounds during exposure always appeared in word-initial position (replacing the first sounds of /f/- or /s/-initial words). No retuning was found. In Experiment 2, the same ambiguous sounds always appeared word-finally during exposure. Here, retuning was found. Lexically guided perceptual learning thus appears to emerge reliably only when lexical knowledge is available as the to-be-tuned segment is initially being processed. Under these conditions, however, lexically guided retuning was position independent: It generalized across syllabic positions. Lexical retuning can thus benefit future recognition of particular sounds wherever they appear in words.

Early use of phonetic information in spoken word recognition: Lexical stress drives eye movements immediately

For optimal word recognition listeners should use all relevant acoustic information as soon as it comes available. Using printed-word eye tracking we investigated when during word processing Dutch listeners use suprasegmental lexical stress information to recognize words. Fixations on targets such as “OCtopus” (capitals indicate stress) were more frequent than fixations on segmentally overlapping but differently stressed competitors (“okTOber”) before segmental information could disambiguate the words. Furthermore, prior to segmental disambiguation, initially stressed words were stronger lexical competitors than noninitially stressed words. Listeners recognize words by immediately using all relevant information in the speech signal.

The temporal distribution of information in audiovisual spoken-word identification

In the present study, we examined the distribution and processing of information over time in auditory and visual speech as it is used in unimodal and bimodal word recognition. English consonant-vowel-consonant words representing all possible initial consonants were presented as auditory, visual, or audiovisual speech in a gating task. The distribution of information over time varied across and within features. Visual speech information was generally fully available early during the phoneme, whereas auditory information was still accumulated. An audiovisual benefit was therefore already found early during the phoneme. The nature of the audiovisual recognition benefit changed, however, as more of the phoneme was presented. More features benefited at short gates rather than at longer ones. Visual speech information plays, therefore, a more important role early during the phoneme rather than later. The results of the study showed the complex interplay of information across modalities and time, since this is essential in determining the time course of audiovisual spoken-word recognition.

Speaking Rate Affects the Perception of Duration as a Suprasegmental Lexical-stress Cue

Three categorization experiments investigated whether the speaking rate of a preceding sentence influences durational cues to the perception of suprasegmental lexical-stress patterns. Dutch two-syllable word fragments had to be judged as coming from one of two longer words that matched the fragment segmentally but differed in lexical stress placement. Word pairs contrasted primary stress on either the first versus the second syllable or the first versus the third syllable. Duration of the initial or the second syllable of the fragments and rate of the preceding context (fast vs. slow) were manipulated. Listeners used speaking rate to decide about the degree of stress on initial syllables whether the syllables’ absolute durations were informative about stress (Experiment 1a) or not (Experiment 1b). Rate effects on the second syllable were visible only when the initial syllable was ambiguous in duration with respect to the preceding rate context (Experiment 2). Absolute second syllable durations contributed little to stress perception (Experiment 3). These results suggest that speaking rate is used to disambiguate words and that rate-modulated stress cues are more important on initial than non-initial syllables. Speaking rate affects perception of suprasegmental information.

Audiovisual benefit for recognition of speech presented with single-talker noise in older listeners

Older listeners are more affected than younger listeners in their recognition of speech in adverse conditions, such as when they also hear a single-competing speaker. In the present study, we investigated with a speeded response task whether older listeners with various degrees of hearing loss benefit under such conditions from also seeing the speaker they intend to listen to. We also tested, at the same time, whether older adults need postperceptual processing to obtain an audiovisual benefit. When tested in a phoneme-monitoring task with single-talker noise present, older (and younger) listeners detected target phonemes more reliably and more rapidly in meaningful sentences uttered by the target speaker when they also saw the target speaker. This suggests that older adults processed audiovisual speech rapidly and efficiently enough to benefit already during spoken sentence processing. Audiovisual benefits for older adults were similar in size to those observed for younger adults in terms of response latencies, but smaller for detection accuracy. Older adults with more hearing loss showed larger audiovisual benefits. Attentional abilities predicted the size of audiovisual response time benefits in both age groups. Audiovisual benefits were found in both age groups when monitoring for the visually highly distinct phoneme /p/ and when monitoring for the visually less distinct phoneme /k/. Visual speech thus provides segmental information about the target phoneme, but also provides more global contextual information that helps both older and younger adults in this adverse listening situation.

Working memory affects older adults’ use of context in spoken-word recognition

Many older listeners report difficulties in understanding speech in noisy situations. Working memory and other cognitive skills may modulate older listeners’ ability to use context information to alleviate the effects of noise on spoken-word recognition. In the present study, we investigated whether verbal working memory predicts older adults’ ability to immediately use context information in the recognition of words embedded in sentences, presented in different listening conditions. In a phoneme-monitoring task, older adults were asked to detect as fast and as accurately as possible target phonemes in sentences spoken by a target speaker. Target speech was presented without noise, with fluctuating speech-shaped noise, or with competing speech from a single distractor speaker. The gradient measure of contextual probability (derived from a separate offline rating study) affected the speed of recognition. Contextual facilitation was modulated by older listeners’ verbal working memory (measured with a backward digit span task) and age across listening conditions. Working memory and age, as well as hearing loss, were also the most consistent predictors of overall listening performance. Older listeners’ immediate benefit from context in spoken-word recognition thus relates to their ability to keep and update a semantic representation of the sentence content in working memory.

Seeing a singer helps comprehension of the song's lyrics.

When listening to speech, we often benefit when also seeing the speaker’s face. If this advantage is not domain specific for speech, the recognition of sung lyrics should also benefit from seeing the singer’s face. By independently varying the sight and sound of the lyrics, we found a substantial comprehension benefit of seeing a singer. This benefit was robust across participants, lyrics, and repetition of the test materials. This benefit was much larger than the benefit for sung lyrics obtained in previous research, which had not provided the visual information normally present in singing. Given that the comprehension of sung lyrics benefits from seeing the singer, just like speech comprehension benefits from seeing the speaker, both speech and music perception appear to be multisensory processes.

Prosodic Temporal Alignment of Co-speech Gestures to Speech Facilitates Referent Resolution

Using a referent detection paradigm, we examined whether listeners can determine the object speakers are referring to by using the temporal alignment between the motion speakers impose on objects and their labeling utterances. Stimuli were created by videotaping speakers labeling a novel creature. Without being explicitly instructed to do so, speakers moved the creature during labeling. Trajectories of these motions were used to animate photographs of the creature. Participants in subsequent perception studies heard these labeling utterances while seeing side-by-side animations of two identical creatures in which only the target creature moved as originally intended by the speaker. Using the cross-modal temporal relationship between speech and referent motion, participants identified which creature the speaker was labeling, even when the labeling utterances were low-pass filtered to remove their semantic content or replaced by tone analogues. However, when the prosodic structure was eliminated by reversing the speech signal, participants no longer detected the referent as readily. These results provide strong support for a prosodic cross-modal alignment hypothesis. Speakers produce a perceptible link between the motion they impose upon a referent and the prosodic structure of their speech, and listeners readily use this prosodic cross-modal relationship to resolve referential ambiguity in word-learning situations.

Suprasegmental lexical stress cues in visual speech can guide spoken-word recognition

Visual cues to the individual segments of speech and to sentence prosody guide speech recognition. The present study tested whether visual suprasegmental cues to the stress patterns of words can also constrain recognition. Dutch listeners use acoustic suprasegmental cues to lexical stress (changes in duration, amplitude, and pitch) in spoken-word recognition. We asked here whether they can also use visual suprasegmental cues. In two categorization experiments, Dutch participants saw a speaker say fragments of word pairs that were segmentally identical but differed in their stress realization (e.g., ˈca-vi from cavia “guinea pig” vs. ˌka-vi from kaviaar “caviar”). Participants were able to distinguish between these pairs from seeing a speaker alone. Only the presence of primary stress in the fragment, not its absence, was informative. Participants were able to distinguish visually primary from secondary stress on first syllables, but only when the fragment-bearing target word carried phrase-level emphasis. Furthermore, participants distinguished fragments with primary stress on their second syllable from those with secondary stress on their first syllable (e.g., pro-ˈjec from projector “projector” vs. ˌpro-jec from projectiel “projectile”), independently of phrase-level emphasis. Seeing a speaker thus contributes to spoken-word recognition by providing suprasegmental information about the presence of primary lexical stress.

Correlation versus causation in multisensory perception

Events are often perceived in multiple modalities. The co-occurring proximal visual and auditory stimuli events are mostly also causally linked to the distal event, which makes it difficult to evaluate whether learned correlation or perceived causation guides binding in multisensory perception. Piano tones are an interesting exception: They are associated with the act of the pianist striking keys, an event that is visible to the perceiver, but directly results from hammers hitting strings, an event that typically is not visible to the perceiver. We examined the influence of seeing the hammer or the keystroke on auditory temporal order judgments (TOJs). Participants judged the temporal order of a dog bark and a piano tone, while seeing the piano stroke shifted temporally relative to its audio signal. Visual lead increased “piano-first” responses in auditory TOJ, but more so if the associated keystroke was visible than if the sound-producing hammer was visible, even though both were equally visually salient. This provides evidence for a learning account of audiovisual perception.