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 1803.04567cs.SDeess.AS
收藏

卷积神经网络与语言嵌入在端到端方言识别中的应用

Convolutional Neural Networks and Language Embeddings for End-to-End Dialect Recognition

Massachusetts Institute of Technology(麻省理工学院);Qatar Computing Research Institute, HBKU(哈马德·本·哈利法大学卡塔尔计算研究所)

Suwon Shon, Ahmed Ali, James Glass

摘要:

方言识别(DID)是普通语言识别(LID)的一种特殊情况,但由于方言之间的语言相似性,这是一个更具挑战性的问题。在本文中,我们提出了一个端到端的DID系统和一个连体神经网络提取语言嵌入。我们在阿拉伯方言语音数据集上使用声学和语言特征进行DID任务:多类型广播3(MGB-3)。端到端DID系统使用三种声学特征进行训练:Mel频率倒谱系数(MFCC),对数Mel尺度滤波器组能量(FBANK)和频谱图能量。我们还研究了一种数据集增强方法,以在有限的数据资源下实现强大的性能。我们的语言特征研究主要集中在使用Siamese网络学习方言之间的相似性和差异性,以便我们可以降低特征维数并提高DID性能。使用单一特征集的最佳系统达到73%的准确率,而使用多个特征的融合系统在由5种方言组成的MGB-3方言测试集上的准确率为78%。实验结果表明,FBANK功能实现略优于MFCC的结果。通过速度扰动的数据集增强似乎为系统增加了显著的鲁棒性。虽然具有语言嵌入的暹罗网络没有达到端到端DID系统那样好的结果,但当在融合系统中结合在一起时,这两种方法具有良好的协同作用。

英文摘要:

Dialect identification (DID) is a special case of general language identification (LID), but a more challenging problem due to the linguistic similarity between dialects. In this paper, we propose an end-to-end DID system and a Siamese neural network to extract language embeddings. We use both acoustic and linguistic features for the DID task on the Arabic dialectal speech dataset: Multi-Genre Broadcast 3 (MGB-3). The end-to-end DID system was trained using three kinds of acoustic features: Mel-Frequency Cepstral Coefficients (MFCCs), log Mel-scale Filter Bank energies (FBANK) and spectrogram energies. We also investigated a dataset augmentation approach to achieve robust performance with limited data resources. Our linguistic feature research focused on learning similarities and dissimilarities between dialects using the Siamese network, so that we can reduce feature dimensionality as well as improve DID performance. The best system using a single feature set achieves 73% accuracy, while a fusion system using multiple features yields 78% on the MGB-3 dialect test set consisting of 5 dialects. The experimental results indicate that FBANK features achieve slightly better results than MFCCs. Dataset augmentation via speed perturbation appears to add significant robustness to the system. Although the Siamese network with language embeddings did not achieve as good a result as the end-to-end DID system, the two approaches had good synergy when combined together in a fused system.

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。

↑