Dataset Information

Surface Electromyography-Based Recognition, Synthesis, and Perception of Prosodic Subvocal Speech.

ABSTRACT: Purpose This study aimed to evaluate a novel communication system designed to translate surface electromyographic (sEMG) signals from articulatory muscles into speech using a personalized, digital voice. The system was evaluated for word recognition, prosodic classification, and listener perception of synthesized speech. Method sEMG signals were recorded from the face and neck as speakers with (n = 4) and without (n = 4) laryngectomy subvocally recited (silently mouthed) a speech corpus comprising 750 phrases (150 phrases with variable phrase-level stress). Corpus tokens were then translated into speech via personalized voice synthesis (n = 8 synthetic voices) and compared against phrases produced by each speaker when using their typical mode of communication (n = 4 natural voices, n = 4 electrolaryngeal [EL] voices). Naïve listeners (n = 12) evaluated synthetic, natural, and EL speech for acceptability and intelligibility in a visual sort-and-rate task, as well as phrasal stress discriminability via a classification mechanism. Results Recorded sEMG signals were processed to translate sEMG muscle activity into lexical content and categorize variations in phrase-level stress, achieving a mean accuracy of 96.3% (SD = 3.10%) and 91.2% (SD = 4.46%), respectively. Synthetic speech was significantly higher in acceptability and intelligibility than EL speech, also leading to greater phrasal stress classification accuracy, whereas natural speech was rated as the most acceptable and intelligible, with the greatest phrasal stress classification accuracy. Conclusion This proof-of-concept study establishes the feasibility of using subvocal sEMG-based alternative communication not only for lexical recognition but also for prosodic communication in healthy individuals, as well as those living with vocal impairments and residual articulatory function. Supplemental Material https://doi.org/10.23641/asha.14558481.

SUBMITTER: Vojtech JM

PROVIDER: S-EPMC8740708 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeCharacterizing and comparing speech recognition development in children with cochlear implants (CIs) is challenging because of variations in test type. This retrospective cohort study modified the Pediatric Ranked Order Speech Perception (PROSPER) scoring system to (a) longitudinally analyze the speech perception of children with CIs and (b) examine the role of age at CI activation, listening mode (i.e., unilateral or bilateral implantation), and interimplant interval.MethodPostimplantation speech recognition scores from 31 children with prelingual, severe-to-profound hearing loss who received CIs were analyzed (12 with unilateral CI [UniCI], 13 with sequential bilateral CIs [SEQ BiCIs], and six with simultaneous BiCIs). Data were extracted from the Massachusetts Eye and Ear Audiology database. A version of the PROSPER score was modified to integrate the varying test types by mapping raw scores from different tests into a single score. The PROSPER scores were used to construct speech recognition growth curves of the implanted ears, which were characterized by the slope of the growth phase, the time from activation to the plateau onset, and the score at the plateau.ResultsWhile speech recognition improved considerably for children following implantation, the growth rates and scores at the plateau were highly variable. In first implanted ears, later implantation was associated with poorer scores at the plateau (β = -0.15, p = .01), but not growth rate. The first implanted ears of children with BiCIs had better scores at the plateau than those with UniCI (β = 0.59, p = .02). Shorter interimplant intervals in children with SEQ BiCIs promoted faster speech recognition growth of the first implanted ears.ConclusionThe modified PROSPER score could be used clinically to track speech recognition development in children with CIs, to assess influencing factors, and to assist in developing and evaluating patient-specific intervention strategies.Supplemental materialhttps://doi.org/10.23641/asha.20113538.

Dataset Information

Surface Electromyography-Based Recognition, Synthesis, and Perception of Prosodic Subvocal Speech.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets