.png){kind=icon}
返回
Forward-Backward Decoding Sequence for Regularizing End-to-End TTS
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2019.2935807.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neural end-to-end TTS such as Tacotron like network can generate very high-quality synthesized speech, and even close to human recording for similar domain text. However, it performs unsatisfactory when scaling it to some challenging test sets. One concern is that the encoder-decoder with attention-based network adopts autoregressive generative sequence model with the limitation of exposure bias: errors made early could be quickly amplified, harming subsequent sequence generation. To address this issue, we propose two novel methods, which aim at predicting future by improving the agreement between forward and backward decoding sequence. The first one (denoted as MRBA) is achieved by adding divergence regularization terms to model training objective to maximize the agreement between two directional models, namely L2R (which generates targets from left-to-right) and R2L (which generates targets from right-to-left). While the second one (denoted as BDR) operates on decoder-level and exploits the future information during decoding. By introducing regularization term into the training objective of forward-backward decoders, the forward-decoder's hidden states are forced to be close to the backward-decoder's. Thus, the hidden representations of a unidirectional decoder are encouraged to embed some useful information about the future. Moreover, in order to make forward and backward decoding to improve each other in an interactive process, a joint training method is designed. Experimental results on both English and Mandarin dataset show that our proposed methods especially the second one (BDR), lead to a significantly improvement on both robustness and overall naturalness, as achieving obvious preference advantages in a challenging test, and achieving state-of-the-art performance (outperforming baseline the revised version of Tacotron2 with a gap of 0.13 and 0.12 for English and Mandarin in MOS, respectively) on a general test.
Keyword:
Decoding
Training
Speech processing
Linguistics
Acoustics
Speech recognition
Forward-backward
regularization
encoder-decoder with attention
end-to-end
joint-training
TTS
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Bioanalytical Approaches for Characterizing Catabolism of Antibody–Drug Conjugates.png)
Bioanalysis
BioanalysisIF0
PREAI
分享收藏Comparative Plastomics of Ashwagandha (Withania, Solanaceae) and Identification of Mutational Hotspots for Barcoding Medicinal Plants药用植物 Ashwagandha (Withania, Solanaceae) 的比较质体基因组学研究及条形码标记中突变热点的鉴定
OAAI
IF0
OAAI分享收藏The dodeca-coordinated La©B8C4+/0/− molecular wheels: conflicting aromaticity versus double aromaticityRSC AdvancesOAAI
RSC AdvancesIF0
OAAI分享收藏分享收藏分享收藏Molecular Characteristics, Antimicrobial Resistance, and Biofilm Formation of Pseudomonas aeruginosa Isolated from Patients with Aural Infections in Shanghai, China铜绿假单胞菌（Pseudomonas aeruginosa）在上海市耳部感染患者中分离株的分子特征、抗菌药物耐药性和生物膜形成能力OAAI
OAAI分享收藏Thermally induced effects on structural and electrical properties of selenium-rich Cd-Se thin films
PREAI
分享收藏
查看更多内容