arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1611.04496cs.CL
收藏

多视角递归神经声学词嵌入

Multi-view Recurrent Neural Acoustic Word Embeddings

Toyota Technological Institute at Chicago(芝加哥丰田技术研究所);University of Chicago(芝加哥大学)

Wanjia He, Weiran Wang, Karen Livescu

摘要:

最近的工作已经开始探索神经声学词嵌入-对应于词的任意长度语音片段的固定维向量表示。这种嵌入适用于语音检索和识别任务,其中关于整个单词的推理可以避免模糊的子单词表示。其主要思想是将声学序列映射到固定维度的向量,使得相同单词的示例映射到相似的向量,而不同单词的示例映射到非常不同的向量。在这项工作中,我们采取了多视角的方法来学习声学词嵌入,其中我们共同学习嵌入声学序列和它们对应的字符序列。我们使用深度双向LSTM嵌入模型和多视图对比损失。我们研究了不同损失变量的影响,包括固定保证金和成本敏感损失。我们的声学词嵌入改善了以前的方法的任务,词歧视。我们还提出了其他任务的结果,使多视图的方法,包括跨视图的单词歧视和单词相似性。

英文摘要:

Recent work has begun exploring neural acoustic word embeddings---fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddings are applicable to speech retrieval and recognition tasks, where reasoning about whole words may make it possible to avoid ambiguous sub-word representations. The main idea is to map acoustic sequences to fixed-dimensional vectors such that examples of the same word are mapped to similar vectors, while different-word examples are mapped to very different vectors. In this work we take a multi-view approach to learning acoustic word embeddings, in which we jointly learn to embed acoustic sequences and their corresponding character sequences. We use deep bidirectional LSTM embedding models and multi-view contrastive losses. We study the effect of different loss variants, including fixed-margin and cost-sensitive losses. Our acoustic word embeddings improve over previous approaches for the task of word discrimination. We also present results on other tasks that are enabled by the multi-view approach, including cross-view word discrimination and word similarity.

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。

↑