Challenge: Grapheme-to-phoneme conversion (g2p) is a task of predicting the pronunciation of words from their orthographic representation.
Approach: They propose to leverage audio data as an auxiliary modality in a multi-task training process to learn a more optimal grapheme representation.
Outcome: The proposed model reduces phoneme error rate to 2.46% on in-domain test set compared to unimodal spelling- pronunciation model.

Similar Papers

Zero-shot Learning for Grapheme to Phoneme Conversion with Language Ensemble (2022.findings-acl)

Copied to clipboard

Challenge: Existing work focuses on low-resource and endangered languages with limited training sets.
Approach: They propose a hypothesis set for any unseen target language and combine it with a confusion network to propose 'the most likely hypothesis' they test the approach on over 600 unseened languages and demonstrate it significantly outperforms baselines.
Outcome: The proposed model outperforms baselines on over 600 unseen languages.
GE2PE: Persian End-to-End Grapheme-to-Phoneme Conversion (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing text-to-speech systems struggle to produce natural speech from grapheme sequences . Grapheme-to phoneme conversion (G2P) systems face limitations when dealing with Persian texts due to the complexity of Persian transcription.
Approach: They propose to use phonetic information to enhance the input sequence for Persian translations.
Outcome: The proposed model surpasses state-of-the-art models by 1.86% in word error rate and 3.42% in homograph disambiguation accuracy.
Supervised Grapheme-to-Phoneme Conversion of Orthographic Schwas in Hindi and Punjabi (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to predict schwa deletion in Hindi are based on prosodic or phonetic analysis.
Approach: They propose to use Hindi grapheme-to-phoneme (G2P) conversion to predict whether a schwa represented in the orthography is pronounced or unpronounced (deleted).
Outcome: The proposed model outperforms existing models on a newly-compiled pronunciation lexicon extracted from various online dictionaries.
Epitran: Precision G2P for Many Languages (L18-1)

Copied to clipboard

Challenge: Epitran is a multilingual, multi-back-end system for grapheme-to-phoneme transduction . it supports 61 languages and is open source under an MIT license .
Approach: Epitran is a multilingual back-end system for grapheme-to-phoneme transduction . it takes word tokens in the orthography of a language and outputs a phonemic representation . Epitran's efficacy has been demonstrated in multiple research projects .
Outcome: Epitran is a multilingual, multi-backend system for grapheme-to-phoneme transduction . it supports 61 languages and is open source under MIT license .
A Two-Step Approach for Data-Efficient French Pronunciation Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Recent studies have addressed intricate phonological phenomena in French, relying on extensive linguistic knowledge or a significant amount of sentence-level pronunciation data.
Approach: They propose a grapheme-to-phoneme and post-lexical processing approach to address French phonological phenomena using sentence-level pronunciation data.
Outcome: The proposed approach mitigates the lack of extensive labeled data and serves as a feasible solution for addressing French phonological phenomena even under resource-constrained environments.
MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs (2026.tacl-1)

Copied to clipboard

Challenge: MultiBLiMP 1.0 is a massively multilingual benchmark of linguistic minimal pairs covering 101 languages and 2 types of subject-verb agreement.
Approach: They propose to use multilingual benchmarks to evaluate linguistic minimal pairs in 101 languages and 2 types of subject-verb agreement to create the minimal pairs.
Outcome: The proposed benchmark covers 101 languages and 2 types of subject-verb agreement, and contains more than 128,000 minimal pairs.
Multimodality for NLP-Centered Applications: Resources, Advances and Frontiers (2022.lrec-1)

Copied to clipboard

Challenge: resurgence of multimodal datasets has attracted significant research interest, but there is no comprehensive survey for this task.
Approach: They present a survey of a multimodal dataset with different modalities according to the applications.
Outcome: The proposed datasets are available online and discuss the new frontier and motivate future researches.
Multimodal neural pronunciation modeling for spoken languages with logographic origin (D18-1)

Copied to clipboard

Challenge: Graphemes of most languages encode pronunciation, though some are more explicit than others . pronunciation modeling in logographic languages requires decomposing logographs into subunits .
Approach: They propose a multimodal approach to predict pronunciation of Cantonese logographic characters using neural networks.
Outcome: The proposed framework improves performance by 18.1% and 25.0% respectively to unimodal and multimodal baselines.
Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text (2026.findings-eacl)

Copied to clipboard

Challenge: Existing multimodal models rely on machine translation, but performance drops for other languages due to limited multilingual multimodal resources.
Approach: They propose a lightweight alignment method that learns only a few linear layers using English text alone to map multilingual text embeddings into multimodal space.
Outcome: M2M achieves strong zero-shot transfer on XTD Text-to-Image retrieval in English and spanish . it learns only a few linear layers to map multilingual text embeddings into multimodal space .
GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing evaluation frameworks focus on English and a handful of high-resource languages, thereby overlooking the realistic performance of large language models in multilingual and lower-resourced scenarios.
Approach: They propose a unified and lightweight framework that integrates 27 benchmarks under a standard ISO 639-3 language identifier system to enable seamless incorporation of new benchmarks.
Outcome: The proposed framework integrates 27 benchmarks under a standard ISO 639-3 language identifier system, allowing for seamless incorporation of new benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations