LSTM-TDNN在2019年多类型广播挑战赛中使用卷积前端进行方言识别
LSTM-TDNN with convolutional front-end for Dialect Identification in the 2019 Multi-Genre Broadcast Challenge
摘要:
本文介绍了一种新的方言识别(DID)系统开发的第五版的多流派广播挑战,细粒度阿拉伯语方言识别(MGB-5 ADI挑战)的任务。该系统通过采用卷积和长短期记忆递归(CLSTM)架构来改进传统DNN x向量性能,以结合卷积神经网络前端用于特征提取和后端递归神经网络捕获更长时间依赖性的优势。此外,我们研究了一个低资源方言在高度不平衡的训练集使用时间尺度修改(TSM)的密集增强。这将话语转换成若干时间拉伸或时间压缩的版本,随后用于训练CLSTM系统而不使用任何其他语料库。在本文中,我们还研究了使用MUSAN和RIR数据集的语音增强,以正常方式增加现有训练数据的数量和多样性。结果表明,首先,CLSTM架构优于传统的DNN x向量实现。其次,采用基于TSM的速度扰动产生一个小的性能改善的不平衡的数据,最后,传统的数据增强技术产生进一步的好处,在相关的说话人和语言识别任务的证据。我们的系统在ASRU 2019上展示的MGB-5 ADI挑战赛的15个参赛项目中获得第二名。
英文摘要:
This paper presents a novel Dialect Identification (DID) system developed for the Fifth Edition of the Multi-Genre Broadcast challenge, the task of Fine-grained Arabic Dialect Identification (MGB-5 ADI Challenge). The system improves upon traditional DNN x-vector performance by employing a Convolutional and Long Short Term Memory-Recurrent (CLSTM) architecture to combine the benefits of a convolutional neural network front-end for feature extraction and a back-end recurrent neural to capture longer temporal dependencies. Furthermore we investigate intensive augmentation of one low resource dialect in the highly unbalanced training set using time-scale modification (TSM). This converts an utterance to several time-stretched or time-compressed versions, subsequently used to train the CLSTM system without using any other corpus. In this paper, we also investigate speech augmentation using MUSAN and the RIR datasets to increase the quantity and diversity of the existing training data in the normal way. Results show firstly that the CLSTM architecture outperforms a traditional DNN x-vector implementation. Secondly, adopting TSM-based speed perturbation yields a small performance improvement for the unbalanced data, finally that traditional data augmentation techniques yield further benefit, in line with evidence from related speaker and language recognition tasks. Our system achieved 2nd place ranking out of 15 entries in the MGB-5 ADI challenge, presented at ASRU 2019.
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。