Phonemizer: Text to Phones Transcription for Multiple Languages in Python

By Mathieu Bernard, Hadrien Titeux. 2021

146 citations recorded by the source corpus.

Phones are elementary sounds the speech is made of, on which syllables and words are built. The transcription of texts from their orthographic form into a phonetic alphabet is an important requirement in various applications related to speech and language processing, for instance for text to speech systems. Phonemizer is a Python package addressing precisely this issue: it transcribes a text from its orthographic representation into a phonetic one. The package is user-friendly and exposes a single high-level phonemize function, a lower lovel API, and is also available as a command-line interface. It supports about a hundred different languages and provides end-user functionalities such as punctuation preservation, phones accentuation, tokenization at phone/syllable/word levels, as well as parallel processing of large input texts.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Experimental and Cognitive Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Sheng Zhao
5. Lei He
6. Frank K. Soong
7. Cong Han
8. Yanqing Liu

In Developmental and Educational Psychology

1. Gavin Mischler
2. Nima Mesgarani
3. Vinay S. Raghavan
4. Xilin Jiang
5. Cong Han

In Experimental and Cognitive Psychology

1. Tao Qin
2. Yichong Leng
3. Gavin Mischler
4. Nima Mesgarani
5. Frank K. Soong
6. Vinay S. Raghavan
7. Tie-Yan Liu
8. Xilin Jiang

Citations in the corpus

• StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models (2023, methodology): “All datasets were resampled to 24 kHz to match LibriTTS, and the texts were converted into phonemes using phonemizer [58].”
• NaturalSpeech: End-to-End Text-to-Speech Synthesis With Human-Level Quality (2022, methodology): “We conduct several preprocessing on the speech and text sequences: 1) We convert the text/character sequence into phoneme sequence [56] using a grapheme-to-phoneme tool [57].”
• PHONEME-LEVEL BERT FOR ENHANCED PROSODY OF TEXT-TO-SPEECH WITH GRAPHEME PREDICTIONS (2023, methodology): “Phonemes are obtained using Phonemizer [14] that converts text sequences into the International Phonetic Alphabets (IPA) with the eSpeak backend.”