Skip to content

Profy

Product or Programme · All products and programmes
Evidence · 1 claim (1 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

Profy is a deep-learning automated pronunciation-feedback system developed by Kazuki Kawamura that evaluates learner speech against native-speaker data and highlights localized deviations for imitation-based skill practice.

Components

  • Profy data-driven pronunciation feedback system learned from unannotated audio: Profy is an automated feedback system for imitation-based skill learning, instantiated for second-language pronunciation. It constructs a deep learning model that "directly learns what constitutes good and poor performance from unannotated audio data", avoiding the annotated error-pattern databases of conventional CAPT systems. The system highlights waveform regions emphasized by the classifier and shows model-derived acoustic distances from native-speaker distributions in latent space, giving learners localized feedback on where their performance deviates. (Kazuki Kawamura (2025))

Claims

-

Key Sources

  • Kazuki Kawamura. (2025). AI-Guided Learning: Research on Knowledge and Skill Acquisition Support Methods Using Deep Learning Audio-Video Processing Techniques. Doctoral dissertation, The University of Tokyo. https://arxiv.org/abs/2608.08990
Page metadata
Field Value
type product
id profy
title Profy
description Profy is a deep-learning automated pronunciation-feedback system developed by Kazuki Kawamura that evaluates learner speech against native-speaker data and highlights localized deviations for imitation-based skill practice.
status review
product_kind software
generated by process:settle-candidates on 2026-10-10
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.