Paper Info
Title
Exploring Transfer Learning between Scripted and Spontaneous Speech for Emotion Recognition.
Abstract
Internet of Things technologies yield large amounts of real-life speech data related to human emotions. Yet, labelled data of human emotion from spontaneous speech are extremely limited due to the difficulties in the annotation of such large volumes of audio samples. A potential way to address this limitation is to augment emotion models of spontaneous speech with fully annotated data collected using scripted scenarios. We investigate whether and to what extent knowledge related to speech emotional content can be transferred between datasets of scripted and spontaneous speech. We implement transfer learning through: (1) a feed-forward neural network trained on the source data and whose last layers are fine-tuned based on the target data; and (2) a progressive neural network retaining a pool of pre-trained models and learning lateral connections between source and target task. We explore the effectiveness of the proposed approach using four publicly available datasets of emotional speech. Our results indicate that transfer learning can effectively leverage corpora of scripted data to improve emotion recognition performance for spontaneous speech.
Year
DOI
Venue
2019
10.1145/3340555.3353762
ICMI
Keywords
Field
DocType
speech emotion recognition, transfer learning, (progressive) neural network, fine tuning
Computer science,Emotion recognition,Transfer of learning,Human–computer interaction
Conference
ISBN
Citations 
PageRank 
978-1-4503-6860-5
0
0.34
References 
Authors
0
2
Name
Order
Citations
PageRank
Qingqing Li100.34
Theodora Chaspari23819.43