Multi-task deep learning for user intention understanding in speech interaction systems
Speech interaction systems have been gaining popularity in recent years. The main purpose
of these systems is to generate more satisfactory responses according to users' speech …
of these systems is to generate more satisfactory responses according to users' speech …
[PDF][PDF] Combining CNN and BLSTM to Extract Textual and Acoustic Features for Recognizing Stances in Mandarin Ideological Debate Competition.
L Li, Z Wu, M Xu, HM Meng, L Cai - Interspeech, 2016 - se.cuhk.edu.hk
Recognizing stances in ideological debates is a relatively new and challenging problem in
opinion mining. While previous work mainly focused on text modality, in this paper, we try to …
opinion mining. While previous work mainly focused on text modality, in this paper, we try to …
Learning cross-lingual knowledge with multilingual BLSTM for emphasis detection with limited training data
Bidirectional long short-term memory (BLSTM) recurrent neural network (RNN) has
achieved state-of-the-art performance in many sequence processing problems given its …
achieved state-of-the-art performance in many sequence processing problems given its …
Emphasis detection for voice dialogue applications using multi-channel convolutional bidirectional long short-term memory network
L Zhang, J Jia, F Meng, S Zhou, W Chen… - … on Chinese Spoken …, 2018 - ieeexplore.ieee.org
Emphasis detection is important for user intention understanding in human-computer
interaction scenario. Techniques have been developed to detect the emphatic words in …
interaction scenario. Techniques have been developed to detect the emphatic words in …
[PDF][PDF] Detection of prominent words in oral reading by children
K Sabu, P Rao - Proceedings of speech prosody, Poznan, Poland, 2018 - isca-archive.org
The evaluation of oral reading skills is considered an important component of language
education in school. Compared with word decoding skill, prosodic fluency typically takes …
education in school. Compared with word decoding skill, prosodic fluency typically takes …
Recognizing stances in mandarin social ideological debates with text and acoustic features
L Li, Z Wu, M Xu, H Meng, L Cai - 2016 IEEE International …, 2016 - ieeexplore.ieee.org
Recognizing stances is of great importance to understand intention of human beings. While
previous related researches mainly focused on text modality, in this paper, we aim to …
previous related researches mainly focused on text modality, in this paper, we aim to …
Learning Contextual Representation with Convolution Bank and Multi-head Self-attention for Speech Emphasis Detection
In speech interaction scenarios, speech emphasis plays an important role in conveying the
underlying intention of the speaker. For better understanding of user intention and further …
underlying intention of the speaker. For better understanding of user intention and further …