Exploiting Low-rank Tensor-train Deep Neural Networks Based On Riemannian Gradient Descent With Illustrations Of Speech Processing
2022 · Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen, et al.
Abstract
This work focuses on designing low complexity hybrid tensor networks by considering trade-offs between the model complexity and practical performance. Firstly, we exploit a low-rank tensor-train deep neural network (TT-DNN) to build an end-to-end deep learning pipeline, namely LR-TT-DNN. Secondly, a hybrid model combining LR-TT-DNN with a convolutional neural network (CNN), which is denoted as CNN+(LR-TT-DNN), is set up to boost the performance. Instead of randomly assigning large TT-ranks for TT-DNN, we leverage Riemannian gradient descent to determine a TT-DNN associated with small TT-ranks. Furthermore, CNN+(LR-TT-DNN) consists of convolutional layers at the bottom for feature extraction and several TT layers at the top to solve regression and classification problems. We separately assess the LR-TT-DNN and CNN+(LR-TT-DNN) models on speech enhancement and spoken command recognition tasks. Our empirical evidence demonstrates that the LR-TT-DNN and CNN+(LR-TT-DNN) models with fewer mod
Authors
(none)
Tags
Stats
Related papers
- Exploring Deep Hybrid Tensor-to-vector Network Architectures For Regression Based Speech Enhancement (2020)7.50
- Tensor-to-vector Regression For Multi-channel Speech Enhancement Based On Tensor-train Network (2020)12.39
- Tensor-train Long Short-term Memory For Monaural Speech Enhancement (2018)0.00
- Lightweight And Efficient End-to-end Speech Recognition Using Low-rank Transformer (2019)0.00
- Developing RNN-T Models Surpassing High-performance Hybrid Models With Customization Capability (2020)13.28
- Multitask Learning And Joint Optimization For Transformer-rnn-transducer Speech Recognition (2020)8.09
- Full-rank No More: Low-rank Weight Training For Modern Speech Recognition Models (2024)2.26
- Improving RNN Transducer Modeling For End-to-end Speech Recognition (2019)0.00