Increasing the intelligibility of speech through multiple phonemic restorations.

Outside of the laboratory, listening conditions are often less than ideal, and when attending to sounds from a particular source, portions are often obliterated by extraneous noises. However, listeners possess rather elegant reconstructive mechanisms. Restoration can be complete, so that missing segments are indistinguishable from those actually present and the listener is unaware that the signal is fragmented. This phenomenon, called temporal induction (TI), has been studied extensively with nonverbal signals and to a lesser extent with speech. Earlier studies have demonstrated that TI can produce illusory continuity spanning gaps of a few hundred milliseconds when portions of a signal are replaced by a louder sound capable of masking the signal were it actually present. The present study employed various types of speech signals with periodic gaps and measured the effects upon intelligibility produced by filling these gaps with noises. Enhancement of intelligibility through multiple phonemic restoration occurred when the acoustic requirements for TI were met and when sufficient contextual information was available in the remaining speech fragments. It appears that phonemic restoration is a specialized form of TI that uses linguistic skills for the reconstruction of obliterated speech.     

Speech perception and phonemic restorations

When a speech sound in a sentence is replaced completely by an extraneous sound (such as a cough or tone), the listene restores the missing sound on the bases of both prior and subsequent context. This illusory effect, called phonemic restoration (PhR), causes the physically absent phoneme to seem as real as the speech sounds which are present. The extraneous sound seems to occur along with other phonemes without interfering with their clarity. But if a silent gap (rather than an extraneous sound) replaces the same phoneme, the interruption in the sentence is more readily localized in its true position and PhRs occours less frequently. Quantitative measures were taken both of the incidence of PhRs and of the direction and extent of temporal mislocalizations of interruptions for several related stimuli under a variety of experimental conditions. The results were connected with other auditory illusions and temporal confusions reported in the literature, and suggestions were made concerning mechanisms employed normally for verbal organization.     

Contrasting speech patterns in apraxia of speech and phonemic paraphasia

This study was designed to determine if perceptual phonological analysis would reveal distinctions between patients with apraxia of speech and patients with phonemic paraphasic speech. Test findings from 10 Broca's aphasics with apraxia of speech were compared to findings from 10 paraphasic speakers (5 conduction and 5 Wernicke's aphasics). Several marked differences were revealed. Predominant locus of errors and relative difficulty of different classes of phonemic segments were significant discriminators. There was a nonsignificant trend for substituted phonemes to be further from target phonetically in the paraphasic patients. In addition, the two groups showed certain consistent differences in the types of errors they produced. Apraxic patients produced many errors of transitionalization, while sequencing errors were more typical of the patients with phonemic paraphasia. The findings are interpreted in relation to a neuropsychological model of speech. It is suggested that phonemic paraphasia represents a breakdown mainly in the retrieval of phonological word patterns, while apraxia of speech is characterized predominantly by a disturbance in encoding phonological patterns into appropriate speech movements.     

Word rate and intelligibility of alternated speech

A continuous speech message alternated between the left and right ears retains generally good intelligibility, except at certain critical rates of alternation of about 3–4 switching cycles/sec. In the present experiment, subjects heard speech alternated between the two ears at eight different switching frequencies, and at four different speech rates. Results support an earlier contention that the critical intelligibility parameter in alternated speech is average speech content per ear segment, rather than absolute time per ear. Implications are discussed both in terms of critical speech segments in auditory analysis and in neural processing of binaural auditory information.     

Magnitude estimation scaling judgments of speech intelligibility and speech acceptability.

20 female students in speech-language pathology provided magnitude estimation scaling responses for the speech intelligibility and acceptability of audio-taped speech samples varying systematically the number of consonant sounds produced correctly. Analysis indicated no significant over-all differences between listeners' judgments of intelligibility and acceptability; however, listeners tended to judge samples with fewer than 50% of the consonants correct as more acceptable than intelligible, and they judged samples with more than 50% consonants correct as less acceptable than intelligible.     

Visual prosody and speech intelligibility: head movement improves auditory speech perception

People naturally move their heads when they speak, and our study shows that this rhythmic head motion conveys linguistic information. Three-dimensional head and face motion and the acoustics of a talker producing Japanese sentences were recorded and analyzed. The head movement correlated strongly with the pitch (fundamental frequency) and amplitude of the talker's voice. In a perception study, Japanese subjects viewed realistic talking-head animations based on these movement recordings in a speech-in-noise task. The animations allowed the head motion to be manipulated without changing other characteristics of the visual or acoustic speech. Subjects correctly identified more syllables when natural head motion was present in the animation than when it was eliminated or distorted. These results suggest that nonverbal gestures such as head movements play a more direct role in the perception of speech than previously known.     

Cross-channel amplitude sweeps are crucial to speech intelligibility

Classical views of speech perception argue that the static and dynamic characteristics of spectral energy peaks (formants) are the acoustic features that underpin phoneme recognition. Here we use representations where the amplitude modulations of sub-band filtered speech are described, precisely, in terms of co-sinusoidal pulses. These pulses are parameterised in terms of their amplitude, duration and position in time across a large number of spectral channels. Coherent sweeps of energy across this parameter space are identified and the local transitions of pulse features across spectral channels are extracted. Synthesised speech based on manipulations of these local amplitude modulation features was used to explore the basis of intelligibility. The results show that removing changes in amplitude across channels has a much greater impact on intelligibility than differences in sweep transition or duration across channels. This finding has severe implications for future experimental design in the fields of psychophysics, electrophysiology and neuroimaging.     

Syllabic and phonemic representations for short-term memory of speech stimuli

An experiment is reported which uses a same-different matching paradigm in which subjects are required to indicate whether the consonants of a pair of consonant-diphthong syllables are the same or different. The question addressed is the operation of two hypothesized processes in the perception of speech sounds. The auditory level is shown to hold stimulus information for a brief period of time and be sensitive to allophonic variations within a stimulus. Moreover, matching at this level takes place by identity of the syllables rather than of the separate phoneme segments. The phonemic level is impaired when the diphthong segments of the pair leads to a contradictory match to that of the consonants of the pair, even though only the consonants are relevant to the matching decision.     

Limited visual control of the intelligibility of speech in face-to-face dialogue

Speakers are thought to articulate individual words in running speech less carefully whenever additional nonacoustic information can help listeners recognize what is said (Fowler & Housum, 1987; Lieberman, 1963). Comparing single words excerpted from spontaneous dialogues and control tokens of the same words read by the same speakers in lists, Experiment 1 yielded a significant but general effect of visual context: Tokens introducing 71 new entities in dialogues in which participants could see one another’s faces were more degraded (less intelligible to 54 naive listeners) than were tokens of the same words from dialogues with sight lines blocked. Loss of clarity was not keyed to momentto-moment visual behavior. Subjects with clear sight lines looked at each other too rarely to account for the observed effect. Experiment 2 revealed that tokens of 60 words uttered while subjects were looking at each other were significantly less degraded (in length and in intelligibility to 72 subjects) vis-à-vis controls than were spontaneous tokens of the same words produced when subjects were looking elsewhere. Intelligibility loss was mitigated only when listeners looked at speakers. Two separate visual effects are discussed, one of the global availability and the other of the local use of the interlocutor’s face.     

Effects of intelligibility on working memory demand for speech perception

Understanding low-intelligibility speech is effortful. In three experiments, we examined the effects of intelligibility on working memory (WM) demands imposed by perception of synthetic speech. In all three experiments, a primary speeded word recognition task was paired with a secondary WM-load task designed to vary the availability of WM capacity during speech perception. Speech intelligibility was varied either by training listeners to use available acoustic cues in a more diagnostic manner (as in Experiment 1) or by providing listeners with more informative acoustic cues (i.e., better speech quality, as in Experiments 2 and 3). In the first experiment, training significantly improved intelligibility and recognition speed; increasing WM load significantly slowed recognition. A significant interaction between training and load indicated that the benefit of training on recognition speed was observed only under low memory load. In subsequent experiments, listeners received no training; intelligibility was manipulated by changing synthesizers. Improving intelligibility without training improved recognition accuracy, and increasing memory load still decreased it, but more intelligible speech did not produce more efficient use of available WM capacity. This suggests that perceptual learning modifies the way available capacity is used, perhaps by increasing the use of more phonetically informative features and/or by decreasing use of less informative ones.     

Inner speech slips exhibit lexical bias, but not the phonemic similarity effect

Inner speech, that little voice that people often hear inside their heads while thinking, is a form of mental imagery. The properties of inner speech errors can be used to investigate the nature of inner speech, just as overt slips are informative about overt speech production. Overt slips tend to create words (lexical bias) and involve similar exchanging phonemes (phonemic similarity effect). We examined these effects in inner and overt speech via a tongue-twister recitation task. While lexical bias was present in both inner and overt speech errors, the phonemic similarity effect was evident only for overt errors, producing a significant overtness by similarity interaction. We propose that inner speech is impoverished at lower (featural) levels, but robust at higher (phonemic) levels.     

A speech-rate intelligibility threshold for speeded and time-compressed connected speech

An automated threshold method has been developed for determining the maximum rate of speech understood by individual listeners. Two experiments were undertaken to determine whether the threshold was related to the comprehension of speech or to speech intelligibility. The first experiment compared thresholds of two types of rapid speech reportedly different in intelligibility: simple speeded speech and speech compressed by the sampling method. The second experiment sought to determine the relationship of the threshold to traditional comprehension measures. The results are discussed in terms of the intelligibility and comprehensibility of speech.     

Test of Spanish sentences to measure speech intelligibility in noise conditions

This article describes the development of a test for measuring the intelligibility of speech in noise for the Spanish language, similar to the test developed by Kalikow, Stevens, and Elliot (Journal of the Acoustical Society of America, 5, 1337–1360, 1977) for the English language. The test consists of six forms, each comprising 25 high-predictability (HP) sentences and 25 low-predictability (LP) sentences. The sentences were used in a perceptual task to assess their intelligibility in babble noise across three different signal-to-noise ratio (SNR) conditions in a sample of 474 normal-hearing listeners. The results showed that the listeners obtained higher scores of intelligibility for HP sentences than for LP sentences, and the scores were lower for the higher SNRs, as was expected. The final six forms were equivalent in intelligibility and phonetic content.