Spoken Word2Vec：从语音中学习 Skipgram 嵌入
Spoken Word2Vec: Learning Skipgram Embeddings from Speech
AI总结：
本文针对口语词语义嵌入易编码语音而非语义的问题，分析浅层 skipgram 失效原因，并提出深度端到端变体以改善嵌入空间的语义相关性。
摘要：
编码分布语义的文本词嵌入通过对高频词的上下文相似性进行建模而起作用。相比之下，声学词嵌入通常编码低层语音相似性。此前已有研究使用类似 Word2Vec 的算法探索口语词的语义嵌入，但所得向量仍主要编码语音特征而非语义特征。本文考察了以往工作采用的假设和架构，并通过实验表明，当输入单元存在声学相关性时，浅层 skipgram 类算法无法编码分布语义。我们展示了该模型的一种深度端到端替代变体的潜力，并考察其对所得嵌入的影响，结果显示嵌入空间中的语义相关性取得了积极效果。
英文摘要：
Text word embeddings that encode distributional semantics work by modeling contextual similarities of frequently occurring words. Acoustic word embeddings, on the other hand, typically encode low-level phonetic similarities. Semantic embeddings for spoken words have been previously explored using analogous algorithms to Word2Vec, but the resulting vectors still mainly encoded phonetic rather than semantic features. In this paper, we examine the assumptions and architectures used in previous works and show experimentally how shallow skipgram-like algorithms fail to encode distributional semantics when the input units are acoustically correlated. We illustrate the potential of an alternative deep end-to-end variant of the model and examine the effects on the resulting embeddings, showing positive results of semantic relatedness in the embedding space.
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。
