Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2018)

引用 15|浏览105
暂无评分
摘要
This paper explores the use of multi-view features and their discriminative transforms in a convolutional deep neural network (CNN) architecture for a continuous large vocabulary speech recognition task. Mel-filterbank energies and perceptually motivated forced damped oscillator coefficient (DOC) features are used after feature-space maximum-likelihood linear regression (fMLLR) transforms, which are combined and fed as a multi-view feature to a single CNN acoustic model. Use of multi-view feature representation demonstrated significant reduction in word error rates (WERs) compared to the use of individual features by themselves. In addition, when articulatory information was used as an additional input to a fused deep neural network (DNN) and CNN acoustic model, it was found to demonstrate further reduction in WER for the Switchboard subset and the CallHome subset (containing partly non-native accented speech) of the NIST 2000 conversational telephone speech test set, reducing the error rate by 12% relative to the baseline in both cases. This work shows that multi-view features in association with articulatory information can improve speech recognition robustness to spontaneous and non-native speech.
更多
查看译文
关键词
multi-view features,feature combination,large vocabulary continuous speech recognition,robust speech recognition,articulatory features
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要