arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.14796cs.CL
收藏

语音词嵌入

Phonetic Word Embeddings

Reliance Jio AI-CoE(信实吉奥人工智能卓越中心)

Rahul Sharma, Kunal Dhawan, Balakrishna Pailla

摘要:

这项工作提出了一种新的方法来计算语音之间的相似性,从人类感知的声音的动机。该度量用于学习连续向量嵌入空间,该空间将相似的发音单词分组在一起,并且可以用于各种下游计算音位学任务。两种不同的语言(英语,印地语)和性能增益比以前报道的作品进行了讨论,建立测试预测语音相似性的方法的功效。为了解决有限的基准机制在这一领域,我们还介绍了一个异质双关语数据集为基础的评估方法来比较声学相似性算法的有效性。此外,嵌入空间的可视化与讨论的各种可能的用例,这种新的算法。还共享了一个开源实现,以帮助再现性并在相关任务中采用。

英文摘要:

This work presents a novel methodology for calculating the phonetic similarity between words taking motivation from the human perception of sounds. This metric is employed to learn a continuous vector embedding space that groups similar sounding words together and can be used for various downstream computational phonology tasks. The efficacy of the method is presented for two different languages (English, Hindi) and performance gains over previous reported works are discussed on established tests for predicting phonetic similarity. To address limited benchmarking mechanisms in this field, we also introduce a heterographic pun dataset based evaluation methodology to compare the effectiveness of acoustic similarity algorithms. Further, a visualization of the embedding space is presented with a discussion on the various possible use-cases of this novel algorithm. An open-source implementation is also shared to aid reproducibility and enable adoption in related tasks.

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。

↑