arXiv Computation and Language
Phoneme-Guided Initialization for LLM-based Speech Recognition
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
5d ago
Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition
arXiv:2603.29217v3 Announce Type: replace-cross Abstract: Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing...
Hugging Face Trending Papers
Sep 23
Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach
Text-to-speech systems increasingly process user-generated text (UGT) such as ppl and imo, whose pronunciation must be inferred from the canonical rather than surface form. We introduce UGTPhon, the f...
arXiv Computation and Language
6d ago
DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs
arXiv:2610.08085v1 Announce Type: new Abstract: Speech-LLMs often exhibit prompt overfitting, where models solely trained on automatic speech recognition (ASR) instruction fail to generalize to new i...
arXiv AI
Sep 24
Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach
The paper introduces UGTPhon, a grapheme-to-phoneme benchmark for user‑generated text in English, Vietnamese, and Korean, and presents a taxonomy for diagnosing pronunciation errors. It shows that existing G2P models and large language models struggle with canonical‑to‑non‑canonical text, with errors up to 66.8 PER points. A compositional G2P approach that uses exact‑match lookup and staged decoding reduces these errors and performs competitively with larger few‑shot LLMs.
arXiv Computation and Language
Aug 28
Scaling phoneme-based TTS augmentation for ASR: A unified pipeline and controlled study
The paper introduces a unified phoneme‑based TTS‑to‑ASR augmentation pipeline that uses a multilingual TTS model with language‑ID conditioning and incorporates grapheme‑to‑phoneme conversion, reference‑speech filtering, and candidate‑text selection. It proposes phoneme‑frequency‑guided selection (PFGS) to rank sentences based on phoneme frequencies from real ASR labels, and demonstrates that random augmentation and PFGS both improve ASR performance across Arabic, French, Italian, and Portuguese test sets, with PFGS yielding up to a 19.3% relative WER reduction. The study also shows that filtering reference speech can further lower WER by up to 0.59 points on certain datasets.
arXiv Computation and Language
Sep 28
Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring
The paper introduces a training‑free speech‑and‑text‑to‑pronunciation (ST2P) pipeline that combines lexical candidates from G2P tools with acoustic rescoring using frozen pretrained S2P models. By performing a left‑to‑right greedy search over whole‑sequence negative log‑likelihoods, the method achieves a dramatic reduction in character error rate on Japanese corpora, outperforming both baseline G2P/S2P approaches and commercial multimodal LLMs. The approach is also significantly faster—3–3.5× faster than beam search and twice as fast as direct decoding—while maintaining high accuracy across multiple languages.