跨语言嵌入聚类用于低资源多语言语音识别中的分层Softmax
Cross-lingual Embedding Clustering for Hierarchical Softmax in Low-Resource Multilingual Speech Recognition
AI总结:
提出一种基于跨语言嵌入聚类构建分层Softmax解码器的方法,通过共享相似令牌表示提升低资源多语言语音识别精度。
摘要:
我们提出了一种新颖的方法,聚焦于自动语音识别(ASR)的解码阶段,以增强多语言性能,特别是对于低资源语言。该方法利用跨语言嵌入聚类方法构建分层Softmax(H-Softmax)解码器,使得不同语言中的相似令牌能够共享相似的解码器表示。它解决了先前基于Huffman的H-Softmax方法的局限性,该方法在令牌相似性评估中依赖浅层特征。通过在15种语言的下采样数据集上的实验,我们证明了该方法在提高低资源多语言ASR准确性方面的有效性。
英文摘要:
We present a novel approach centered on the decoding stage of Automatic Speech Recognition (ASR) that enhances multilingual performance, especially for low-resource languages. It utilizes a cross-lingual embedding clustering method to construct a hierarchical Softmax (H-Softmax) decoder, which enables similar tokens across different languages to share similar decoder representations. It addresses the limitations of the previous Huffman-based H-Softmax method, which relied on shallow features in token similarity assessments. Through experiments on a downsampled dataset of 15 languages, we demonstrate the effectiveness of our approach in improving low-resource multilingual ASR accuracy.
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。