学习用于数据增强的跨语言映射以改进低资源语音识别
Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition
AI总结：
针对低资源语言语音识别数据稀缺问题，提出可学习跨语言映射方法，无需平行数据即可实现源语言转写并用于数据增强，相对单语言基线模型最高提升5%性能。
摘要：
利用跨语言资源是弥补低资源语言数据稀缺的有效途径。近期，学界提出了一种新颖的多语言模型融合技术，该技术训练模型将跨语言声学-语音相似性作为映射函数进行学习。不过，现有方法依赖人工构建的词典来训练混合DNN-HMM（深度神经网络-隐马尔可夫模型）ASR（自动语音识别）系统。为消除这种依赖，我们将可学习跨语言映射的概念拓展至端到端语音识别场景。此外，我们利用映射模型在无需平行数据的情况下，将源语言转写为目标语言。最后，将源音频及其转写结果用于数据增强，以重新训练目标语言ASR模型。实验结果表明，任意源语言ASR模型搭配所提出的映射模型后，均可用于低资源目标语言识别。此外，相较于单语言基线模型，数据增强带来了最高达5%的相对性能提升。
英文摘要：
Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. Recently, a novel multilingual model fusion technique has been proposed where a model is trained to learn cross-lingual acoustic-phonetic similarities as a mapping function. However, handcrafted lexicons have been used to train hybrid DNN-HMM ASR systems. To remove this dependency, we extend the concept of learnable cross-lingual mappings for end-to-end speech recognition. Furthermore, mapping models are employed to transliterate the source languages to the target language without using parallel data. Finally, the source audio and its transliteration is used for data augmentation to retrain the target language ASR. The results show that any source language ASR model can be used for a low-resource target language recognition followed by proposed mapping model. Furthermore, data augmentation results in a relative gain up to 5% over baseline monolingual model.
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。
