arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.10329eess.AScs.LGcs.SDstat.ML
收藏

声学邻居嵌入

Acoustic Neighbor Embeddings

Apple(苹果公司)

Woojay Jeon

摘要:

本文提出了一种新的声学字嵌入称为声学邻居嵌入语音或文本的任意长度被映射到一个向量空间的固定,减少尺寸通过适应随机邻居嵌入(SNE)顺序输入。嵌入空间中坐标之间的欧氏距离反映了其对应序列之间的语音混淆性。训练两个编码器神经网络:声学编码器,其接受从声学模型获得的逐帧子字后验概率形式的语音信号,以及文本编码器,其接受子字transmittance形式的文本。与三重损失准则相比,所提出的方法具有更有效的神经网络训练梯度。在实验上,当两个编码器网络在单词(名称)识别任务中串联使用时,以及当文本编码器网络在近似语音匹配任务中独立使用时,它也给出了更准确的低维嵌入结果。特别是,在一个孤立的名称识别任务,仅依赖于建议的嵌入向量之间的欧几里德最近邻搜索,识别精度是相同的传统的有限状态转换器(FST)的解码使用测试数据与多达1万个名称的词汇和40个维度的嵌入。

英文摘要:

This paper proposes a novel acoustic word embedding called Acoustic Neighbor Embeddings where speech or text of arbitrary length are mapped to a vector space of fixed, reduced dimensions by adapting stochastic neighbor embedding (SNE) to sequential inputs. The Euclidean distance between coordinates in the embedding space reflects the phonetic confusability between their corresponding sequences. Two encoder neural networks are trained: an acoustic encoder that accepts speech signals in the form of frame-wise subword posterior probabilities obtained from an acoustic model and a text encoder that accepts text in the form of subword transcriptions. Compared to a triplet loss criterion, the proposed method is shown to have more effective gradients for neural network training. Experimentally, it also gives more accurate results with low-dimensional embeddings when the two encoder networks are used in tandem in a word (name) recognition task, and when the text encoder network is used standalone in an approximate phonetic matching task. In particular, in an isolated name recognition task depending solely on Euclidean nearest-neighbor search between the proposed embedding vectors, the recognition accuracy is identical to that of conventional finite state transducer(FST)-based decoding using test data with up to 1 million names in the vocabulary and 40 dimensions in the embeddings.

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。

↑