Perceptual formant discrimination during speech movement planning

Abstract

Evoked potential studies have shown that speech planning modulates auditory cortical responses. The phenomenon's functional relevance is unknown. We tested whether, during this time window of cortical auditory modulation, there is an effect on speakers' perceptual sensitivity for vowel formant discrimination. Participants made same/different judgments for pairs of stimuli consisting of a pre-recorded, self-produced vowel and a formant-shifted version of the same production. Stimuli were presented prior to a "go" signal for speaking, prior to passive listening, and during silent reading. The formant discrimination stimulus /uh/ was tested with a congruent productions list (words with /uh/) and an incongruent productions list (words without /uh/). Logistic curves were fitted to participants' responses, and the just-noticeable difference (JND) served as a measure of discrimination sensitivity. We found a statistically significant effect of condition (worst discrimination before speaking) without congruency effect. Post-hoc pairwise comparisons revealed that JND was significantly greater before speaking than during silent reading. Thus, formant discrimination sensitivity was reduced during speech planning regardless of the congruence between discrimination stimulus and predicted acoustic consequences of the planned speech movements. This finding may inform ongoing efforts to determine the functional relevance of the previously reported modulation of auditory processing during speech planning.

Keywords: auditory feedback; formant discrimination; sensory gating; sensory modulation; sensory prediction; speech production.

Fig 1.. Experimental Procedure.

Each trial started with a white word on a black screen. During the white word period, two truncated vowels, a standard stimulus (at 290 ms) and a comparison stimulus (at 450 ms), were played to the participants. The word changed to green at 600 ms and this color change served as the go signal in the Speaking condition. In the Listening condition, participants listened to playback of their own production after the word changed to green. In the Reading condition, participants silently read the word. At 2000 ms, the green word disappeared and the participants were asked to judge whether the standard and comparison stimuli sounded the same or different by pressing keys on a keyboard.

Fig 2.. Boxplots illustrating exclusion of an outlier participant.

(A) just-noticeable difference (JND) averaged across all six tasks. (B) JND by condition (Reading, Speaking, Listening) and word list. The cross symbol (×) indicates the participant who was excluded because the JND averaged across the six tasks was more than three absolute deviations (grey bars) away from the sample median (grey dots).

Fig 3.. Formant Discrimination Task Results.

(A) Logistic curves fitted to group averaged data for the proportion of “Different” responses by condition and word list. (B) Mean and individual participant JNDs by condition and word list. (C) Mean and individual participant slopes by condition and word list. JND and slope were calculated from the logistic curves fitted to each participant’s responses in each task. (D) Mean keypress response time at each formant shift level of the comparison stimulus by condition and word list. Error bars correspond to standard errors.