1 |
Correcting Misproducted Speech using Spectrogram Inpainting ...
|
|
|
|
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 ... : under submission to Interspeech 2022 ...
|
|
Keyword:
Audio and Speech Processing eess.AS; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.2204.03379 https://arxiv.org/abs/2204.03379
|
|
BASE
|
|
Hide details
|
|
2 |
DeepFry: Identifying Vocal Fry Using Deep Neural Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Using automated acoustic analysis to explore the link between planning and articulation in second language speech production ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Using automated acoustic analysis to explore the link between planning and articulation in second language speech production ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Phoneme Boundary Detection using Learnable Segmental Features ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
The influence of lexical selection disruptions on articulation
|
|
|
|
In: J Exp Psychol Learn Mem Cogn (2018)
|
|
BASE
|
|
Show details
|
|
10 |
Learning Similarity Functions for Pronunciation Variations ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
SEQUENCE SEGMENTATION USING JOINT RNN AND STRUCTURED PREDICTION MODELS
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Sequence Segmentation Using Joint RNN and Structured Prediction Models ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Automatic measurement of vowel duration via structured prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Automatic measurement of vowel duration via structured prediction
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Discriminative Keyword Spotting
|
|
|
|
In: http://infoscience.epfl.ch/record/146043 (2010)
|
|
BASE
|
|
Show details
|
|
17 |
A Proposal for a Kernel-based Algorithm for Large Vocabulary Continuous Speech Recognition
|
|
|
|
In: http://infoscience.epfl.ch/record/146084 (2010)
|
|
BASE
|
|
Show details
|
|
|
|