T5G2P: Text-to-Text Transfer Transformer Based Grapheme-to-Phoneme Conversion

IF 4.1 2区计算机科学 Q1 ACOUSTICS

IEEE/ACM Transactions on Audio, Speech, and Language Processing Pub Date : 2024-07-10 DOI:10.1109/TASLP.2024.3426332

Markéta Řezáčková;Daniel Tihelka;Jindřich Matoušek

引用次数: 0

Abstract

The present paper explores the use of several deep neural network architectures to carry out a grapheme-to-phoneme (G2P) conversion, aiming to find a universal and language-independent approach to the task. The models explored are trained on whole sentences in order to automatically capture cross-word context (such as voicedness assimilation) if it exists in the given language. Four different languages, English, Czech, Russian, and German, were chosen due to their different nature and requirements for the G2P task. Ultimately, the Text-to-Text Transfer Transformer (T5) based model achieved very high conversion accuracy on all the tested languages. Also, it exceeded the accuracy reached by a similar system, when trained on a public LibriSpeech database.

查看原文本刊更多论文

T5G2P：基于词素到音素转换的文本到文本转换器

本文探讨了使用几种深度神经网络架构进行词素到音素（G2P）转换的方法，旨在找到一种通用的、与语言无关的方法来完成这项任务。所探索的模型是在整个句子中进行训练的，以便自动捕捉特定语言中存在的跨词语境（如声母同化）。由于英语、捷克语、俄语和德语这四种语言的性质和对 G2P 任务的要求不同，因此选择了这四种语言。最终，基于文本到文本转换器（T5）的模型在所有测试语言中都达到了非常高的转换精度。此外，它还超过了在公共 LibriSpeech 数据库上训练的类似系统所达到的准确率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE/ACM Transactions on Audio, Speech, and Language Processing ACOUSTICS-ENGINEERING, ELECTRICAL & ELECTRONIC

CiteScore

11.30

自引率

11.10%

发文量

217

期刊介绍： The IEEE/ACM Transactions on Audio, Speech, and Language Processing covers audio, speech and language processing and the sciences that support them. In audio processing: transducers, room acoustics, active sound control, human audition, analysis/synthesis/coding of music, and consumer audio. In speech processing: areas such as speech analysis, synthesis, coding, speech and speaker recognition, speech production and perception, and speech enhancement. In language processing: speech and text analysis, understanding, generation, dialog management, translation, summarization, question answering and document indexing and retrieval, as well as general language modeling.