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 1804.00385eess.AScs.LGcs.SD
收藏

一种用于端到端语言识别的可学习词典编码层

A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification

Sun Yat-sen University(中山大学);Duke Kunshan University(昆山杜克大学);Tencent Inc.(腾讯公司);Jiangsu Jinling Science and Technology Group Limited(江苏金陵科技集团有限公司)

Weicheng Cai, Zexin Cai, Xiang Zhang, Xiaoqi Wang, Ming Li

摘要:

本文提出了一种新的可学习的字典编码层,用于端到端的语言识别。该方法与传统的GMM i向量方法在理论和实践上都是一致的。在CNN的基础上,模拟了传统的GMM训练机制和超向量编码过程。该层可以从可变长度的输入序列中累积高阶统计量,并生成话语级固定维向量表示。与传统方法不同,我们的新方法提供了一个端到端的学习框架,其中固有的字典直接从损失函数中学习。字典和分类器的编码表示是联合学习的。该表示是无序的,因此适合于语言识别。我们在NIST LRE 07闭集任务上进行了初步实验,结果表明,与简单的平均池化相比,我们提出的字典编码层实现了显着的错误减少。

英文摘要:

A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification. It is inline with the conventional GMM i-vector approach both theoretically and practically. We imitate the mechanism of traditional GMM training and Supervector encoding procedure on the top of CNN. The proposed layer can accumulate high-order statistics from variable-length input sequence and generate an utterance level fixed-dimensional vector representation. Unlike the conventional methods, our new approach provides an end-to-end learning framework, where the inherent dictionary are learned directly from the loss function. The dictionaries and the encoding representation for the classifier are learned jointly. The representation is orderless and therefore appropriate for language identification. We conducted a preliminary experiment on NIST LRE07 closed-set task, and the results reveal that our proposed dictionary encoding layer achieves significant error reduction comparing with the simple average pooling.

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。

↑