Low-Resource G2P and P2G Conversion with Synthetic Training Data

Hauer, Bradley; Habibi, Amir Ahmad; Luan, Yixing; Mallik, Arnob; Kondrak, Grzegorz

doi:10.18653/v1/2020.sigmorphon-1.12

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grapheme-to-phoneme (G2P) conversion generates a phonetic transcription from the written form of words. It is essential to develop a phonemic lexicon for TTS and ASR systems [1][2][3][4]. For this purpose, G2P techniques are used.…”

Section: Introductionmentioning

confidence: 99%

r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled noise introducing and Contextual information incorporation

Zhao¹,

Wang²,

Qu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Grapheme-to-phoneme (G2P) conversion is the process of converting the written form of words to their pronunciations. It has an important role for text-to-speech (TTS) synthesis and automatic speech recognition (ASR) systems. In this paper, we aim to evaluate and enhance the robustness of G2P models. We show that neural G2P models are extremely sensitive to orthographical variations in graphemes like spelling mistakes.To solve this problem, we propose three controlled noise introducing methods to synthesize noisy training data. Moreover, we incorporate the contextual information with the baseline and propose a robust training strategy to stabilize the training process. The experimental results demonstrate that our proposed robust G2P model (r-G2P) outperforms the baseline significantly (-2.73% WER on Dict-based benchmarks and -9.09% WER on Real-world sources).

show abstract

Section: Introductionmentioning

confidence: 99%