Correcting Mispronunciations in Speech using Spectrogram Inpainting

TL;DR

This paper introduces a deep learning inpainting system using spectrogram masking to correct mispronunciations in speech, maintaining speaker identity and providing synthetic feedback for language learners and children with pronunciation issues.

Contribution

It presents a novel spectrogram inpainting approach with a U-net architecture to generate corrected speech while preserving speaker voice, trained on proper speech examples.

Findings

Listeners slightly prefer the generated speech over simple phoneme replacement.

The system effectively reconstructs correct pronunciations in minimal pairs.

It shows promise for aiding language learning and speech therapy.

Abstract

Learning a new language involves constantly comparing speech productions with reference productions from the environment. Early in speech acquisition, children make articulatory adjustments to match their caregivers' speech. Grownup learners of a language tweak their speech to match the tutor reference. This paper proposes a method to synthetically generate correct pronunciation feedback given incorrect production. Furthermore, our aim is to generate the corrected production while maintaining the speaker's original voice. The system prompts the user to pronounce a phrase. The speech is recorded, and the samples associated with the inaccurate phoneme are masked with zeros. This waveform serves as an input to a speech generator, implemented as a deep learning inpainting system with a U-net architecture, and trained to output a reconstructed speech. The training set is composed of unimpaired proper speech examples, and the generator is trained to reconstruct the original proper speech. We evaluated the performance of our system on phoneme replacement of minimal pair words of English as well as on children with pronunciation disorders. Results suggest that human listeners slightly prefer our generated speech over a smoothed replacement of the inaccurate phoneme with a production of a different speaker.