Temporal feature extraction based on CNN-BLSTM and temporal pooling for language identification
Authors:
- Xiuyan LiuXLXiuyan Liu
- Chen ChenCCChen Chen
- Yongjun HeYHYongjun He
- 3 June 2022
- journal article
- research article
- Published by Elsevier in Applied Acoustics
- Vol. 195
Abstract
No abstract availableKeywords
Funding Information
- Heilongjiang Postdoctoral Science Foundation (LBH-Z20020)
- National Natural Science Foundation of China (62101163)
- China Postdoctoral Science Foundation (2021M701020)
- Natural Science Foundation of Heilongjiang Province (LH2021F029)
This publication has 10 references indexed in Scilit:
- Multi-Query Multi-Head Attention Pooling and Inter-Topk Penalty for Speaker Verification2022
- AP19-OLR Challenge: Three Tasks and Their Baselines2019
- Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System2018
- Spoken Language Recognition using X-vectors2018
- Deep neural network-based speaker embeddings for end-to-end speaker verification2017
- Rank Pooling for Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Automatic language identification using deep neural networks2014
- Spoken Language Recognition: From Fundamentals to PracticeProceedings of the IEEE, 2013
- Language recognition via i-vectors and dimensionality reduction2011
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000