多语言自监督语音表征提升带语码转换的低资源非洲语言语音识别
Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching
AI总结：
针对低资源非洲语言语码转换语音数据集过小难以训练模型的问题，提出微调 wav2vec 2.0 XLSR 等自监督多语言表征并结合 n-gram 语言模型，使绝对词错率最多降低 20%，是数据有限时的更优方案。
摘要：
尽管低资源语言使用者经常在其母语与其他区域语言或英语之间进行语码转换，但语码转换语音数据集规模太小，无法从头训练定制声学模型或进行语言模型重打分。为此，我们提出微调自监督语音表征（如 wav2vec 2.0 XLSR）来识别语码转换数据。我们发现，微调自监督多语言表征，并结合从转录本训练的 n-gram 语言模型进行增强，与在语码转换数据上从头训练的混合模型基线相比，绝对词错率最多降低了 20%。研究结果表明，在训练数据有限的情况下，微调自监督表征是性能更优且可行的解决方案。
英文摘要：
While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language model rescoring. Here we propose finetuning self-supervised speech representations such as wav2vec 2.0 XLSR to recognize code-switched data. We find that finetuning self-supervised multilingual representations and augmenting them with n-gram language models trained from transcripts reduces absolute word error rates by up to 20% compared to baselines of hybrid models trained from scratch on code-switched data. Our findings suggest that in circumstances with limited training data finetuning self-supervised representations is a better performing and viable solution.
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。
