Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition

• URL: http://arxiv.org/abs/2603.29217v1
• Date: Tue, 31 Mar 2026 03:32:18 GMT
• Title: Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition
• Abstract summary: Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G)
• Score: 7.1298369596156475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing while keeping language-specific orthography in a separate module. While large language models (LLMs) are promising for P2G, multilingual P2G remains challenging due to language-aware generation and severe cross-language data imbalance. We study multilingual LLM-based P2G on the ten-language CV-Lang10 benchmark. We examine robustness strategies that account for S2P uncertainty, including DANP and Simplified SKM (S-SKM). S-SKM is a Monte Carlo approximation that avoids CTC-based S2P probability weighting in P2G training. Robust training and low-resource oversampling reduce the average WER from 10.56% to 7.66%.

Related papers

• An Empirical Recipe for Universal Phone Recognition [63.45609714127985]
  Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks.<n>We present PhoneticXEUS -- trained on large-scale multilingual data.<n>We achieve state-of-the-art performance on both multilingual (17.7% PFER) and accented English speech (10.6% PFER)
  arXiv  Detail & Related papers  (2026-03-30T22:12:48Z)
• Towards Unsupervised Speech Recognition at the Syllable-Level [95.54031547995874]
  We introduce a syllable-level UASR framework based on masked language modeling.<n>We generalize effectively to Mandarin, a language that has remained particularly difficult for prior methods.
  arXiv  Detail & Related papers  (2025-10-04T02:56:33Z)
• Pronunciation-Lexicon Free Training for Phoneme-based Crosslingual ASR via Joint Stochastic Approximation [12.39451124683428]
  We propose a latent variable model based method, with phonemes being treated as discrete latent variables.<n>Based on a multilingual pre-trained S2P model, crosslingual experiments are conducted in Polish and Indonesian.<n>With only 10 minutes of phoneme supervision, the new method, JSA-SPG, achieves 5% error rate reductions.
  arXiv  Detail & Related papers  (2025-07-04T12:23:22Z)
• Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR [23.285609467633865]
  This paper introduces the integration of language-specific bi-directional context into a speech large language model (SLLM) to improve multilingual continuous conversational automatic speech recognition (ASR)<n>We propose a character-level contextual masking strategy during training, which randomly removes portions of the context to enhance robustness and better emulate the flawed transcriptions that may occur during inference.
  arXiv  Detail & Related papers  (2025-06-16T12:03:23Z)
• LLM-based phoneme-to-grapheme for phoneme-based speech recognition [11.552927239284582]
  We propose phoneme-to-grapheme (LLM-P2G) decoding for phoneme-based automatic speech recognition (ASR)<n>Our experimental results show that LLM-P2G outperforms WFST-based systems in crosslingual ASR for Polish and German, by relative WER reductions of 3.6% and 6.9% respectively.
  arXiv  Detail & Related papers  (2025-06-05T07:35:55Z)
• Zero-resource Speech Translation and Recognition with LLMs [38.11535502039386]
  We propose to leverage a multilingual Large Language Model (LLM) to perform ST and ASR in languages for which the model has never seen paired audio-text data.<n>We achieve this by using a pre-trained multilingual speech encoder, a multilingual LLM, and a lightweight adaptation module that maps the audio representations to the token embedding space of the LLM.
  arXiv  Detail & Related papers  (2024-12-24T17:37:11Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• Generalizing Multimodal Pre-training into Multilingual via Language Acquisition [54.69707237195554]
  English-based Vision-Language Pre-training has achieved great success in various downstream tasks. Some efforts have been taken to generalize this success to non-English languages through Multilingual Vision-Language Pre-training. We propose a textbfMultitextbfLingual textbfAcquisition (MLA) framework that can easily generalize a monolingual Vision-Language Pre-training model into multilingual.
  arXiv  Detail & Related papers  (2022-05-29T08:53:22Z)
• Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition [58.849768879796905]
  We propose Adapt-and-Adjust (A2), a transformer-based multi-task learning framework for end-to-end multilingual speech recognition. The A2 framework overcomes the long-tail problem via three techniques: (1) exploiting a pretrained multilingual language model (mBERT) to improve the performance of low-resource languages; (2) proposing dual adapters consisting of both language-specific and language-agnostic adaptation with minimal additional parameters; and (3) overcoming the class imbalance, either by imposing class priors in the loss during training or adjusting the logits of the softmax output during inference.
  arXiv  Detail & Related papers  (2020-12-03T03:46:16Z)
• Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation [105.41167108465085]
  Cross-lingual Machine Reading (CLMRC) remains a challenging problem due to the lack of large-scale datasets in low-source languages. We propose a novel augmentation approach named Language Branch Machine Reading (LBMRC) LBMRC trains multiple machine reading comprehension (MRC) models proficient in individual language. We devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages.
  arXiv  Detail & Related papers  (2020-10-27T13:12:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.