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.
@article{arxiv.2308.03917,
title = {Universal Automatic Phonetic Transcription into the International Phonetic Alphabet},
author = {Chihiro Taguchi and Yusuke Sakai and Parisa Haghani and David Chiang},
journal= {arXiv preprint arXiv:2308.03917},
year = {2023}
}