Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
A Regression Approach to Speech Enhancement Based on Deep Neural Networks
TLDR
The proposed DNN approach can well suppress highly nonstationary noise, which is tough to handle in general, and is effective in dealing with noisy speech data recorded in real-world scenarios without the generation of the annoying musical artifact commonly observed in conventional enhancement methods.
View on ACM
An Experimental Study on Speech Enhancement Based on Deep Neural Networks
TLDR
This letter presents a regression-based speech enhancement framework using deep neural networks (DNNs) with a multiple-layer deep architecture that tends to achieve significant improvements in terms of various objective quality measures.
View on IEEE
WaveNet Vocoder with Limited Training Data for Voice Conversion
TLDR
Experimental results show that the WaveNet vocoders built using the proposed method outperform conventional STRAIGHT vocoder, and the system achieves an average naturalness MOS of 4.13 in VCC 2018, which is the highest among all submitted systems.
View via Publisher
The Fixed-Size Ordinally-Forgetting Encoding Method for Neural Network Language Models
TLDR
Experimental results have shown that without using any recurrent feedbacks, FOFE based FNNLMs can significantly outperform not only the standard fixed-input FNN-LMs but also the popular recurrent neural network (RNN) LMs.
View on ACL
Multiple-target deep learning for LSTM-RNN based speech enhancement
TLDR
The proposed framework can consistently and significantly improve the objective measures for both speech quality and intelligibility and a novel multiple-target joint learning approach is designed to fully utilize this complementarity.
View on IEEE
Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition
TLDR
This study improves the encoder by employing densely connected convolutional networks as they can strengthen feature extraction and facilitate gradient propagation especially on a small training set and presents a novel multi-scale attention model which is employed to deal with the recognition of math symbols in different scales and restore the fine-grained details dropped by pooling operations.
View on IEEE
Non-Parallel Sequence-to-Sequence Voice Conversion With Disentangled Linguistic and Speaker Representations
TLDR
In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion is achieved by preserving the linguistic representations of source utterances while replacing the speaker representations with the target ones in sequence-to-sequence (seq2seq) voice conversion.
View on IEEE
Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
TLDR
Experimental results have shown FSMNs significantly outperform the conventional recurrent neural networks (RNN) in modeling sequential signals like speech or language and can be learned much more reliably and faster than RNNs or LSTMs due to the inherent non-recurrent model structure.
View PDF on arXiv
i-vector representation based on bottleneck features for language identification
TLDR
An i-vector representation based on bottleneck (BN) features is presented for language identification (LID) and the resulting performance of LID has been significantly improved with the proposed BN feature based i- vector representation.
View via Publisher
Dynamic noise aware training for speech enhancement based on deep neural networks
TLDR
Three algorithms to address the mismatch problem in deep neural network (DNN) based speech enhancement are proposed and can well suppress highly non-stationary noise better than all the competing state-of-the-art techniques.
View Paper
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License