Ladder networks for emotion recognition: Using unsupervised auxiliary tasks to improve predictions of emotional attributes
S Parthasarathy, C Busso - arXiv preprint arXiv:1804.10816, 2018 - arxiv.org
Recognizing emotions using few attribute dimensions such as arousal, valence and
dominance provides the flexibility to effectively represent complex range of emotional …
dominance provides the flexibility to effectively represent complex range of emotional …
[HTML][HTML] Emotion recognition support system: Where physicians and psychiatrists meet linguists and data engineers
An important factor in the course of daily medical diagnosis and treatment is understanding
patients' emotional states by the caregiver physicians. However, patients usually avoid …
patients' emotional states by the caregiver physicians. However, patients usually avoid …
Time-scale feature extractions for emotional speech characterization: applied to human centered interaction analysis
Emotional speech characterization is an important issue for the understanding of interaction.
This article discusses the time-scale analysis problem in feature extraction for emotional …
This article discusses the time-scale analysis problem in feature extraction for emotional …
Mismatched feature detection with finer granularity for emotional speaker recognition
L Chen, Y Yang, Z Wu - Journal of Zhejiang University SCIENCE C, 2014 - Springer
The shapes of speakers' vocal organs change under their different emotional states, which
leads to the deviation of the emotional acoustic space of short-time features from the neutral …
leads to the deviation of the emotional acoustic space of short-time features from the neutral …
Emotional speech characterization based on multi-features fusion for face-to-face interaction
A Mahdhaoui, F Ringeval… - 2009 3rd International …, 2009 - ieeexplore.ieee.org
Speech contains non verbal elements known as paralanguage, including voice quality,
emotion and speaking style, as well as prosodic features such as rhythm, intonation and …
emotion and speaking style, as well as prosodic features such as rhythm, intonation and …
用于情感说话人识别的精细失真特征检测与修正
L Chen, Y Yang, Z Wu, AL Chen, AY Yang… - Journal of Zhejiang …, 2014 - jzus.zju.edu.cn
研究目的: 说话人情感变化时其发音器官会发生形变, 导致部分语音特征分布较中性条件下发生
一定偏移. 这些发生偏移的特征使得说话人识别性能大幅下降, 称作" 失真特征", 需剔除或修正 …
一定偏移. 这些发生偏移的特征使得说话人识别性能大幅下降, 称作" 失真特征", 需剔除或修正 …
[PDF][PDF] Predicting treatment outcomes in dysarthria through speech feature analysis.
AR Fletcher - 2016 - ir.canterbury.ac.nz
Increasing loudness and reducing speech rate are common behavioural speech
modifications used in the treatment of dysarthria. Both strategies provide a promising basis …
modifications used in the treatment of dysarthria. Both strategies provide a promising basis …