paper-with-me

홈 › Papers

Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models

2022-01-26 · Lu Dong, Zhi-Qiang Guo, Chao-Hong Tan, Ya-Jun Hu, Yuan Jiang, Zhen-Hua Ling

Neural network models have achieved state-of-the-art performance on grapheme-to-phoneme (G2P) conversion. However, their performance relies on large-scale pronunciation dictionaries, which may not be available for a lot of languages. Inspired by the success of the pre-trained language model BERT, this paper proposes a pre-trained grapheme model called grapheme BERT (GBERT), which is built by self-supervised training on a large, language-specific word list with only grapheme information. Furthermore, two approaches are developed to incorporate GBERT into the state-of-the-art Transformer-based G2P model, i.e., fine-tuning GBERT or fusing GBERT into the Transformer model by attention. Experimental results on the Dutch, Serbo-Croatian, Bulgarian and Korean datasets of the SIGMORPHON 2021 G2P task confirm the effectiveness of our GBERT-based G2P models under both medium-resource and low-resource data conditions.

📄 PDF Abstract BibTeX arXiv:2201.10716

Code (1)

ldong1111/graphemebert 공식 구현 pytorch

Tasks

Grapheme-to-Phoneme ConversionLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
WordPiece 설명 없음
Weight Decay 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

An Investigation of the Relation Between Grapheme Embeddings and Pronunciation for Tacotron-based Systems

2020-10-21 · Antoine Perquin, Erica Cooper, Junichi Yamagishi

End-to-end models, particularly Tacotron-based ones, are currently a popular solution for text-to-speech synthesis. They allow the production of high-quality synthesized speech with little to no text preprocessing. Indee…

Grapheme-to-Phoneme ConversionRelationSpeech Synthesistext-to-speech+2

Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models

2024-11-12 · Dongrui Han, Mingyu Cui, Jiawen Kang, Xixin Wu 외

Grapheme-to-phoneme (G2P) conversion is a crucial step in Text-to-Speech (TTS) systems, responsible for mapping grapheme to corresponding phonetic representations. However, it faces ambiguities problems where the same gr…

Grapheme-to-Phoneme ConversionRetrievaltext-to-speechText to Speech

The SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion

2020-07-01 · WS 2020 7 · Kyle Gorman, Lucas F.E. Ashby, Aaron Goyzueta, Arya McCarthy 외

We describe the design and findings of the SIGMORPHON 2020 shared task on multilingual grapheme-to-phoneme conversion. Participants were asked to submit systems which take in a sequence of graphemes in a given language a…

Grapheme-to-Phoneme Conversion

Grapheme-to-Phoneme Conversion with a Multilingual Transformer Model

2020-07-01 · WS 2020 7 · Omnia ElSaadany, Benjamin Suter

In this paper, we describe our three submissions to the SIGMORPHON 2020 shared task 1 on grapheme-to-phoneme conversion for 15 languages. We experimented with a single multilingual transformer model. We observed that the…

Grapheme-to-Phoneme Conversion

Results of the Second SIGMORPHON Shared Task on Multilingual Grapheme-to-Phoneme Conversion

2021-08-01 · ACL (SIGMORPHON) 2021 8 · Lucas F.E. Ashby, Travis M. Bartley, Simon Clematide, Luca Del Signore 외

Grapheme-to-phoneme conversion is an important component in many speech technologies, but until recently there were no multilingual benchmarks for this task. The second iteration of the SIGMORPHON shared task on multilin…

Grapheme-to-Phoneme Conversion