Compact Graph Architecture for Speech Emotion Recognition

Published in

IEEE International Conference on Acoustics, Spe...(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

The proposed deep graph approach to address the task of speech emotion recognition achieves state-of-the-art performance with significantly fewer learnable parameters and outperforms standard GCN and other relevant deep graph architectures indicating the effectiveness of the approach.

Abstract

We propose a deep graph approach to address the task of speech emotion recognition. A compact, efficient and scalable way to represent data is in the form of graphs. Following the theory of graph signal processing, we propose to model speech signal as a cycle graph or a line graph. Such graph structure enables us to construct a Graph Convolution Network (GCN)-based architecture that can perform an accurate graph convolution in contrast to the approximate convolution used in standard GCNs. We evaluated the performance of our model for speech emotion recognition on the popular IEMOCAP and MSP-IMPROV databases. Our model outperforms standard GCN and other relevant deep graph architectures indicating the effectiveness of our approach. When compared with existing speech emotion recognition methods, our model achieves comparable performance to the state-of-the-art with significantly fewer learnable parameters (~30K) indicating its applicability in resource-constrained devices. Our code is available at /github.com/AmirSh15/Compact_SER.

Authors

T. Guha

3 papers

A. Shirian

1 papers

References32 items

Deep Learning of Segment-Level Feature Representation with Multiple Instance Learning for Utterance-Level Speech Emotion Recognition

Few-Shot Audio Classification with Attentional Graph Neural Networks

Graph Convolutional Tracking

Direct Modelling of Speech Emotion from Raw Speech

How Powerful are Graph Neural Networks?

Compact Graph Architecture for Speech Emotion Recognition

Published in

IEEE International Conference on Acoustics, Spe...(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

T. Guha

3 papers

A. Shirian

1 papers

References32 items

Deep Learning of Segment-Level Feature Representation with Multiple Instance Learning for Utterance-Level Speech Emotion Recognition

Few-Shot Audio Classification with Attentional Graph Neural Networks

Graph Convolutional Tracking

Direct Modelling of Speech Emotion from Raw Speech

How Powerful are Graph Neural Networks?

Graph Convolutional Networks for Text Classification

Exploring Spatio-Temporal Representations by Integrating Attention-based Bidirectional-LSTM-RNNs and FCNs for Speech Emotion Recognition

Investigation on Joint Representation Learning for Robust Feature Extraction in Speech Emotion Recognition

Towards Temporal Modelling of Categorical Speech Emotion Recognition

Hierarchical Graph Representation Learning with Differentiable Pooling

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Learning Spontaneity to Improve Emotion Recognition In Speech

Graph Signal Processing: Overview, Challenges, and Applications

Pooling acoustic and lexical features for the prediction of valence

emHealth: Towards Emotion Health Through Depression Prediction and Intelligent Health Recommender System

Speech Emotion Recognition with Emotion-Pair Based Framework Considering Emotion Distribution Information in Dimensional Emotion Space

Progressive Neural Networks for Transfer Learning in Emotion Recognition

Automatic speech emotion recognition using recurrent neural networks with local attention

Semi-Supervised Classification with Graph Convolutional Networks

Attention Assisted Discovery of Sub-Utterance Structure in Speech Emotion Recognition

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Learning Convolutional Neural Networks for Graphs

Speech emotion recognition with acoustic and lexical features

Spectral Networks and Locally Connected Networks on Graphs

Recent developments in openSMILE, the munich open-source multimedia feature extractor

The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains

Understanding the difficulty of training deep feedforward neural networks

IEMOCAP: interactive emotional dyadic motion capture database

An End-to-End Deep Learning Framework with Speech Emotion Recognition of Atypical Individuals

Emotion Communication System

MSP-IMPROV: An Acted Corpus of Dyadic Interactions to Study Emotion Perception

The INTERSPEECH 2009 emotion challenge

Field of Study

Computer ScienceEngineering

Journal Information

Name

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Page

4270-4274

Venue Information

Name

IEEE International Conference on Acoustics, Speech, and Signal Processing

Type

conference

URL

http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000002

Alternate Names

Int Conf Acoust Speech Signal Process
IEEE Int Conf Acoust Speech Signal Process
ICASSP
International Conference on Acoustics, Speech, and Signal Processing