CycleFlow: Leveraging Cycle Consistency in Flow Matching for Speaker Style Adaptation [PDF]
Voice Conversion (VC) aims to convert the style of a source speaker, such as timbre and pitch, to the style of any target speaker while preserving the linguistic content. However, the ground truth of the converted speech does not exist in a non-parallel VC scenario, which induces the train-inference mismatch problem.
arxiv
Efficacy Of Vocal Cord Medialization by Injection Thyroplasty Using Liquid Paraffin In Relieving Hoarseness Of Voice In Idiopathic And Traumatic Unilateral Vocal Cord Paralysis [PDF]
Objective: The objective of the study was to measure the efficacy of injection thyroplasty by liquid paraffin in the medialization of vocal cords in permanent post-traumatic or idiopathic hoarseness.
Alamgir, Ashar+5 more
core +2 more sources
NdYAG laser treatment of a glomus tympanicum tumour [PDF]
Glomus tympanicum tumours are highly vascular tumours of the middle ear. Their removal by conventional surgical methods requires an extensive procedure in many cases, often with ossicular disarticulation to allow adequate exposure prior to the 'chaotic ...
Bown, SG, Grant, HR, Robinson, PJ
core +1 more source
Follow‐up of patients with mild COVID‐19 using subjective, acoustic, and aerodynamic measurements
Abstract Objectives To gain a comprehensive understanding of the vocal repercussions experienced by mild COVID‐19 infection, as well as the duration and underlying factors contributing to these effects. Methods Ten participants with mild COVID‐19 infection were included as the experimental group to evaluate the voice metrics changes at 15 days (D15 ...
Zhi‐Xue Xiao+8 more
wiley +1 more source
Abstract Frankfurt gave an account of “bullshit” as a statement made without regard to truth or falsity. Austin argued that a large amount of language consists of speech acts aimed at goals other than truth or falsity. We don't want our account of bullshit to include all performatives.
Kenny Easwaran
wiley +1 more source
Quantum Approaches for Dysphonia Assessment in Small Speech Datasets [PDF]
Dysphonia, a prevalent medical condition, leads to voice loss, hoarseness, or speech interruptions. To assess it, researchers have been investigating various machine learning techniques alongside traditional medical assessments. Convolutional Neural Networks (CNNs) have gained popularity for their success in audio classification and speech recognition.
arxiv
A survey of voice quality disorders among high school students of the eastern and western New England Dialect regions. [PDF]
Thesis (Ed.M.)--Boston ...
Sahlberg, Richard Arthur
core +1 more source
Correlation of Endotracheal Tube Size with Sore Throat and Hoarseness Following General Anesthesia [PDF]
David Michael Stout+3 more
openalex +1 more source
Clinical Efficacy Analysis of Unilateral Modified Arytenoidectomy for Bilateral Vocal Fold Paralysis
ABSTRACT Purpose To explore the clinical efficacy of unilateral modified arytenoidectomy (UMA) in the treatment of bilateral vocal fold paralysis(BVFP) based on animal models. Methods The UMA which had been tested in excised canine larynges with simulated BVFP was adapted into a clinical technique. The characteristics of this surgical technique involve
Lu Xing, Shu‐Yi Zeng, Pei‐Yun Zhuang
wiley +1 more source