Universal Automatic Phonetic Transcription into the International Phonetic Alphabet

Chihiro Taguchi, Yusuke Sakai, Parisa Haghani, David Chiang
8/7/2023
cs.CLcs.SDeess.AS

No official code found. Best implementation: ctaguchi/multipa (81 stars, last commit 2025-02-28).

Abstract

This paper presents a state-of-the-art model for transcribing speech in any language into the International Phonetic Alphabet (IPA). Transcription of spoken languages into IPA is an essential yet time-consuming process in language documentation, and even partially automating this process has the potential to drastically speed up the documentation of endangered languages. Like the previous best speech-to-IPA model (Wav2Vec2Phoneme), our model is based on wav2vec 2.0 and is fine-tuned to predict IPA from audio input. We use training data from seven languages from CommonVoice 11.0, transcribed into IPA semi-automatically. Although this training dataset is much smaller than Wav2Vec2Phoneme's, its higher quality lets our model achieve comparable or better results. Furthermore, we show that the quality of our universal speech-to-IPA models is close to that of human annotators.

View on arXivView PDF

Code Implementations(1)

ctaguchi/multipaCommunity100%

Universal multilingual automatic speech transcription into IPA

8114PythonMay 18, 20231 years ago

Similar Papers

PolyVoice: Language Models for Speech to Speech Translation

85% match2023

AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation

85% match2023

SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

85% match3 repos11.9k2023

AudioPaLM: A Large Language Model That Can Speak and Listen

84% match2023

Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages

84% match2026

Speech Translation with Large Language Models: An Industrial Practice

84% match2023

Cite this paper

@article{taguchi2023universal,
  title  = {Universal Automatic Phonetic Transcription into the International Phonetic Alphabet},
  author = {Chihiro Taguchi and Yusuke Sakai and Parisa Haghani and David Chiang},
  year   = {2023},
  eprint = {2308.03917},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.03917v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.03917.svg)](https://codeofpaper.com/paper/2308.03917)

Discussion