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 2102.02074cs.SDcs.LGeess.AS
收藏

使用密码短语相关深度自动编码器的文本相关说话人确认数据生成

Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification

Indian Institute of Information Technology(印度信息技术学院);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);LORIA(洛林计算机科学及其应用研究所);Aalborg University(奥尔堡大学)

Achintya Kumar Sarkar, Md Sahidullah, Zheng-Hua Tan

摘要:

在本文中,我们提出了一种新的方法,训练基于密码短语特定深度神经网络(PP-DNN)的自动编码器,以创建用于文本相关说话人验证(TD-SV)的增强数据。每个PP-DNN自动编码器使用目标登记集中可用的特定密码短语的话语通过两种方法来训练:(i)迁移学习和(ii)从头开始训练。接下来,给定话语的特征向量被馈送到PP-DNN,并且来自帧级的每个PP-DNN的输出被认为是一组新的生成数据。然后,从每个PP-DNN生成的数据用于构建TD-SV系统,这与仅考虑可用的评估数据的传统方法相反。所提出的方法可以被认为是使用由每个PP-DNN学习的非线性变换将数据变换到密码短语特定空间。该方法开发了几个TD-SV系统,其数量等于为每个密码短语单独训练的PP-DNN的数量。最后,不同的TD-SV系统的得分进行融合决策。实验在RedDots挑战2016数据库上进行,用于使用短话语的TD-SV。实验结果表明,该方法结合高斯混合模型-通用背景模型(GMM-UBM)和i-向量框架,对传统倒谱特征和深度瓶颈特征都有较好的识别性能。

英文摘要:

In this paper, we propose a novel method that trains pass-phrase specific deep neural network (PP-DNN) based auto-encoders for creating augmented data for text-dependent speaker verification (TD-SV). Each PP-DNN auto-encoder is trained using the utterances of a particular pass-phrase available in the target enrollment set with two methods: (i) transfer learning and (ii) training from scratch. Next, feature vectors of a given utterance are fed to the PP-DNNs and the output from each PP-DNN at frame-level is considered one new set of generated data. The generated data from each PP-DNN is then used for building a TD-SV system in contrast to the conventional method that considers only the evaluation data available. The proposed approach can be considered as the transformation of data to the pass-phrase specific space using a non-linear transformation learned by each PP-DNN. The method develops several TD-SV systems with the number equal to the number of PP-DNNs separately trained for each pass-phrases for the evaluation. Finally, the scores of the different TD-SV systems are fused for decision making. Experiments are conducted on the RedDots challenge 2016 database for TD-SV using short utterances. Results show that the proposed method improves the performance for both conventional cepstral feature and deep bottleneck feature using both Gaussian mixture model - universal background model (GMM-UBM) and i-vector framework.

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。

↑