ZIPA: A family of efficient models for multilingual phone recognition
Jian Zhu, Farhan Samir, Eleanor Chodroff, David R. Mortensen
Abstract
We present ZIPA, a family of efficient speech models that advances the state-of-the-art performance of crosslinguistic phone recognition. We first curated IPA PACK++, a large-scale multilingual speech corpus with 17,000+ hours of normalized phone transcriptions and a novel evaluation set capturing unseen languages and sociophonetic variation. ZIPA, including transducer (ZIPA-T) and CTC-based (ZIPA-CR) variants, leverages the efficient Zipformer backbones and outperforms existing phone recognition systems with much fewer parameters. Further scaling via noisy student training on 11,000+ hours of pseudo-labeled multilingual data yields further improvement. While ZIPA achieves strong performance on benchmarks, error analysis reveals persistent limitations in modeling sociophonetic diversity, underscoring challenges for future research.
BibTeX
@inproceedings{zhu-etal-2025-zipa,
title = "{ZIPA}: A family of efficient models for multilingual phone recognition",
author = "Zhu, Jian and
Samir, Farhan and
Chodroff, Eleanor and
Mortensen, David R.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.961/",
doi = "10.18653/v1/2025.acl-long.961",
pages = "19568--19585",
ISBN = "979-8-89176-251-0"
}