ACL Findings2022
Zero-shot Learning for Grapheme to Phoneme Conversion with Language Ensemble
Xinjian Li, Florian Metze, David R. Mortensen, Shinji Watanabe, Alan W. Black
Abstract
Grapheme-to-Phoneme (G2P) has many applications in NLP and speech fields. Most existing work focuses heavily on languages with abundant training datasets, which limits the scope of target languages to less than 100 languages. This work attempts to apply zero-shot learning to approximate G2P models for all lowresource and endangered languages in Glottolog (about 8k languages). For any unseen target language, we first build the phylogenetic tree (i.e. language family tree) to identify top-k nearest languages for which we have training sets. Then we run models of those languages to obtain a hypothesis set, which we combine into a confusion network to propose a most likely hypothesis as an approximation to the target language. We test our approach on over 600 unseen languages and demonstrate it significantly outperforms baselines. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers3
- Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech RepresentationsJeong Hun Yeo, Minsu Kim, Chae Won Kim, Stavros Petridis et al.ICCV 2025 · 3 citations
- LAMA-UT: Language Agnostic Multilingual ASR Through Orthography Unification and Language-Specific TransliterationSangmin Lee, Woo-Jin Chung, Hong-Goo KangAAAI 2025 · 1 citation
- LingGym: How Far Are LLMs from Thinking Like Field Linguists?Changbing Yang, Franklin Ma, Freda Shi, Jian ZhuEMNLP 2025
Builds on1
Related papers
- Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 LanguagesWietse de Vries, Martijn Wieling, Malvina NissimACL 2022 · 63 citations
- ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language AdaptersVipul Rathore, Rajdeep Dhingra, Parag Singla, MausamEMNLP 2023
- Detecting Languages Unintelligible to Multilingual Models through Local Structure ProbesLouis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, Sarath ChandarEMNLP Findings 2022 · 2 citations
- GE2PE: Persian End-to-End Grapheme-to-Phoneme ConversionElnaz Rahmati, Hossein SametiEMNLP Findings 2024 · 2 citations
- YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for EveryoneEdresson Casanova, Julian Weber, Christopher Dane Shulby, Arnaldo Cândido Júnior et al.ICML 2022 · 602 citations
