Dataset Information

Speaking without vocal folds using a machine-learning-assisted wearable sensing-actuation system.

ABSTRACT: Voice disorders resulting from various pathological vocal fold conditions or postoperative recovery of laryngeal cancer surgeries, are common causes of dysphonia. Here, we present a self-powered wearable sensing-actuation system based on soft magnetoelasticity that enables assisted speaking without relying on the vocal folds. It holds a lightweighted mass of approximately 7.2 g, skin-alike modulus of 7.83 × 10⁵Pa, stability against skin perspiration, and a maximum stretchability of 164%. The wearable sensing component can effectively capture extrinsic laryngeal muscle movement and convert them into high-fidelity and analyzable electrical signals, which can be translated into speech signals with the assistance of machine learning algorithms with an accuracy of 94.68%. Then, with the wearable actuation component, the speech could be expressed as voice signals while circumventing vocal fold vibration. We expect this approach could facilitate the restoration of normal voice function and significantly enhance the quality of life for patients with dysfunctional vocal folds.

SUBMITTER: Che Z

PROVIDER: S-EPMC10933441 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Speaking without vocal folds using a machine-learning-assisted wearable sensing-actuation system.

Che Ziyuan Z Wan Xiao X Xu Jing J Duan Chrystal C Zheng Tianqi T Chen Jun J

Nature communications 20240312 1

Voice disorders resulting from various pathological vocal fold conditions or postoperative recovery of laryngeal cancer surgeries, are common causes of dysphonia. Here, we present a self-powered wearable sensing-actuation system based on soft magnetoelasticity that enables assisted speaking without relying on the vocal folds. It holds a lightweighted mass of approximately 7.2 g, skin-alike modulus of 7.83 × 10<sup>5 </sup>Pa, stability against skin perspiration, and a maximum stretchability of 1 ...[more]

PMID: 38472193

Similar Datasets

Project description:Vocal fold (VF) fibrosis, often caused by phonosurgery, radiation, or trauma, leads to irreversible voice dysfunction due to excessive ECM deposition and increased tissue stiffness. VF fibrosis, a significant cause of chronic dysphonia, lacks FDA-approved treatments, highlighting the critical need for novel antifibrotic therapeutic. TGF-β1 is a major driver in the pathological transformation of fibroblasts into contractile myofibroblasts in VF fibrosis via SMAD3, YAP1, and integrin signaling pathways. These pathways lead to increased ACTA2 expression, excessive collagen production, and progressive tissue stiffening. Leveraging the principle that local cells respond to tissue-specific signals, our ECM hydrogel derived from decellularized vocal fold lamina propria (VFLP-ECM) reduced ACTA2 expression in TGF-β1 stimulated vocal fold fibroblasts, showcasing antifibrotic potential. In this study, we evaluated the therapeutic potential of VFLP-ECM hydrogel in a rabbit VF injury model—treatment involved VFLP-ECM or bovine type I collagen injections into VFs 7 days after injury, with evaluations at 28 days post-injury. We compared two VFLP-ECM formulations: a manual process (VFLP (man)) and an accelerated automated method (VFLP (au)). VFLP (man) showed more modulated fibrosis-associated gene expressions when compared to VFLP (au) and collagen. Proteomic analysis revealed that VFLP (man) preserves a broader array of bioactive proteins, such as vitronectin, crucial in TGF-β1 signaling and ECM remodeling. The transcriptomic analysis uncovered a downregulation of key fibrotic markers and potential inhibition of regulators such as SMAD3, YAP1, and MRTFA, alongside the upregulation of SMAD7, an inhibitor of TGF-β signaling. Notably, treatment with VFLP (man) resulted in vocal folds with similar stiffness as uninjured controls, whereas tissues treated with collagen or VFLP (au) remained stiffer, indicating incomplete mechanical recovery. These data provide the first in vivo evidence that VFLP-ECM hydrogel—mainly when produced via manual decellularization—attenuates fibrosis by disrupting biochemical and biomechanical drivers of myofibroblast activation.

Dataset Information

Speaking without vocal folds using a machine-learning-assisted wearable sensing-actuation system.

Publications

Speaking without vocal folds using a machine-learning-assisted wearable sensing-actuation system.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets