.png){kind=icon}
返回
An E2E-ASR-Based Iteratively-Trained Timestamp Estimator
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2022.3190793.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Text-to-speech alignment, also known as time alignment, is essential for automatic speech recognition (ASR) systems used for speech retrieval tasks, such as keyword search and speech segment extraction. Previous works have used the Gaussian mixture model-hidden Markov model (GMM-HMM) forced alignment to improve the alignment performance. However, when used with end-to-end (E2E) ASR, GMM-HMM forced alignment causes extra reliance on expertise such as pronunciation lexica. It also increases the system complexity because GMM-HMMs are very dissimilar to E2E models. To tackle these two problems, we propose an E2E-ASR-based iteratively-trained timestamp estimator (ITSE), which performs alignment between token-level transcription and speech. We train ITSE first with coarse initial alignment targets generated using connectionist temporal classification (CTC) posteriors. During training, we iteratively perform realignment to update the targets. We attribute the effectiveness of the iterative training to ITSE's two vital features. First, ITSE performs alignment using similarities between token and speech embeddings instead of frame-wise token classification posteriors. Second, ITSE uses speech embeddings that are aware of left context rather than global context. ITSE significantly outperforms CTC-based baselines in word alignment accuracy and is comparable to a GMM-HMM forced aligner. In short, ITSE is an accurate, lightweight text-to-speech alignment module implemented without expertise such as pronunciation lexica.
Keyword:
Training
Hidden Markov models
Acoustics
Task analysis
Electronic mail
Decoding
Neural networks
Automatic speech recognition
end-to-end
text-to-speech alignment
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
.png){kind=icon}
分享收藏Magnetic Susceptibility Properties of Loess From the Willendorf Archaeological Site: Implications for the Syn/Post-Depositional Interpretation of Magnetic Fabric维伦多夫考古遗址黄土的磁化率特性：对磁组构成/后沉积解释的启示
OAAI
OAAI分享收藏Potentilla L. (Rosaceae) in the former USSR; second part: comments Notes on Potentilla XXIV委陵菜属 Potentilla L. (蔷薇科 Rosaceae) 在前苏联地区的分布；第二部分：评注《委陵菜属研究笔记》第二十四期
PREAI
分享收藏
分享收藏
查看更多内容