Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912283608743936 |
|---|---|
| author | Han, Dongrui Cui, Mingyu Kang, Jiawen Wu, Xixin Liu, Xunying Meng, Helen |
| author_facet | Han, Dongrui Cui, Mingyu Kang, Jiawen Wu, Xixin Liu, Xunying Meng, Helen |
| contents | Grapheme-to-phoneme (G2P) conversion is a crucial step in Text-to-Speech (TTS) systems, responsible for mapping grapheme to corresponding phonetic representations. However, it faces ambiguities problems where the same grapheme can represent multiple phonemes depending on contexts, posing a challenge for G2P conversion. Inspired by the remarkable success of Large Language Models (LLMs) in handling context-aware scenarios, contextual G2P conversion systems with LLMs' in-context knowledge retrieval (ICKR) capabilities are proposed to promote disambiguation capability. The efficacy of incorporating ICKR into G2P conversion systems is demonstrated thoroughly on the Librig2p dataset. In particular, the best contextual G2P conversion system using ICKR outperforms the baseline with weighted average phoneme error rate (PER) reductions of 2.0% absolute (28.9% relative). Using GPT-4 in the ICKR system can increase of 3.5% absolute (3.8% relative) on the Librig2p dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07563 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models Han, Dongrui Cui, Mingyu Kang, Jiawen Wu, Xixin Liu, Xunying Meng, Helen Artificial Intelligence Grapheme-to-phoneme (G2P) conversion is a crucial step in Text-to-Speech (TTS) systems, responsible for mapping grapheme to corresponding phonetic representations. However, it faces ambiguities problems where the same grapheme can represent multiple phonemes depending on contexts, posing a challenge for G2P conversion. Inspired by the remarkable success of Large Language Models (LLMs) in handling context-aware scenarios, contextual G2P conversion systems with LLMs' in-context knowledge retrieval (ICKR) capabilities are proposed to promote disambiguation capability. The efficacy of incorporating ICKR into G2P conversion systems is demonstrated thoroughly on the Librig2p dataset. In particular, the best contextual G2P conversion system using ICKR outperforms the baseline with weighted average phoneme error rate (PER) reductions of 2.0% absolute (28.9% relative). Using GPT-4 in the ICKR system can increase of 3.5% absolute (3.8% relative) on the Librig2p dataset. |
| title | Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2411.07563 |