arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.03312cs.CLcs.SDeess.AS
收藏

优化两遍跨语言迁移学习:音素识别与音素到字素翻译

Optimizing Two-Pass Cross-Lingual Transfer Learning: Phoneme Recognition and Phoneme to Grapheme Translation

POSTECH(浦项科技大学);aiXplain Inc.(aiXplain公司)

Wonjun Lee, Gary Geunbae Lee, Yunsu Kim

AI总结:

针对低资源语言两遍跨语言 ASR,本文通过发音特征合并音素并引入全局音素噪声生成器,优化音素识别与音素到字素翻译,在 CommonVoice 12.0 上显著降低 WER。

摘要:

本研究通过增强音素识别和音素到字素翻译模型,优化低资源语言中的两遍跨语言迁移学习。我们的方法对这两个阶段进行优化,以提升跨语言语音识别性能。我们通过依据共同发音特征合并音素来优化音素词汇覆盖率,从而提高识别准确率。此外,我们引入全局音素噪声生成器,在音素到字素训练期间生成逼真的 ASR 噪声,以减少误差传播。在 CommonVoice 12.0 数据集上的实验表明,低资源语言的词错误率(WER)显著降低,凸显了本方法的有效性。本研究推动了低资源语言两遍 ASR 系统的进步,并为改进跨语言迁移学习提供了潜力。

英文摘要:

This research optimizes two-pass cross-lingual transfer learning in low-resource languages by enhancing phoneme recognition and phoneme-to-grapheme translation models. Our approach optimizes these two stages to improve speech recognition across languages. We optimize phoneme vocabulary coverage by merging phonemes based on shared articulatory characteristics, thus improving recognition accuracy. Additionally, we introduce a global phoneme noise generator for realistic ASR noise during phoneme-to-grapheme training to reduce error propagation. Experiments on the CommonVoice 12.0 dataset show significant reductions in Word Error Rate (WER) for low-resource languages, highlighting the effectiveness of our approach. This research contributes to the advancements of two-pass ASR systems in low-resource languages, offering the potential for improved cross-lingual transfer learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑