Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Two-Step Approach for Data-Efficient French Pronunciation Learning

Hoyeon Lee, Hyeeun Jang, Jong-Hwan Kim, Jae-Min Kim

TL;DR

This work proposes a novel two-step approach that encompasses two pronunciation tasks: grapheme-to-phoneme and post-lexical processing, and investigates the efficacy of the proposed approach with a notably limited amount of sentence-level pronunciation data.

Abstract

Recent studies have addressed intricate phonological phenomena in French, relying on either extensive linguistic knowledge or a significant amount of sentence-level pronunciation data. However, creating such resources is expensive and non-trivial. To this end, we propose a novel two-step approach that encompasses two pronunciation tasks: grapheme-to-phoneme and post-lexical processing. We then investigate the efficacy of the proposed approach with a notably limited amount of sentence-level pronunciation data. Our findings demonstrate that the proposed two-step approach effectively mitigates the lack of extensive labeled data, and serves as a feasible solution for addressing French phonological phenomena even under resource-constrained environments.

A Two-Step Approach for Data-Efficient French Pronunciation Learning

TL;DR

This work proposes a novel two-step approach that encompasses two pronunciation tasks: grapheme-to-phoneme and post-lexical processing, and investigates the efficacy of the proposed approach with a notably limited amount of sentence-level pronunciation data.

Abstract

Recent studies have addressed intricate phonological phenomena in French, relying on either extensive linguistic knowledge or a significant amount of sentence-level pronunciation data. However, creating such resources is expensive and non-trivial. To this end, we propose a novel two-step approach that encompasses two pronunciation tasks: grapheme-to-phoneme and post-lexical processing. We then investigate the efficacy of the proposed approach with a notably limited amount of sentence-level pronunciation data. Our findings demonstrate that the proposed two-step approach effectively mitigates the lack of extensive labeled data, and serves as a feasible solution for addressing French phonological phenomena even under resource-constrained environments.
Paper Structure (23 sections, 4 equations, 1 figure, 3 tables)

This paper contains 23 sections, 4 equations, 1 figure, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Proposed Method
  4. Grapheme-to-Phoneme
  5. Post-lexical Phonetization
  6. Experiment
  7. Datasets
  8. Experimental Setup
  9. Results and Analysis
  10. Can the baseline models address phonological phenomena?
  11. How effective is the two-step approach in addressing phonological phenomena?
  12. How many sentence-level phonetic transcriptions are needed for our approach to work well?
  13. Conclusion
  14. Limitations
  15. Complexities of French Liaison
  16. ...and 8 more sections

Figures (1)

  • Figure 1: An overview of our proposed architecture.