EmotionNAS: Two-stream Neural Architecture Search for Speech Emotion Recognition

TL;DR

EmotionNAS introduces a two-stream neural architecture search framework for speech emotion recognition, automatically optimizing model structures for different feature types, leading to state-of-the-art performance.

Contribution

The paper presents a novel two-stream NAS framework that effectively combines handcrafted and deep features for SER, reducing manual design effort and improving accuracy.

Findings

Outperforms existing models on SER benchmarks

Sets new state-of-the-art results

Effectively integrates complementary features

Abstract

Speech emotion recognition (SER) is an important research topic in human-computer interaction. Existing works mainly rely on human expertise to design models. Despite their success, different datasets often require distinct structures and hyperparameters. Searching for an optimal model for each dataset is time-consuming and labor-intensive. To address this problem, we propose a two-stream neural architecture search (NAS) based framework, called \enquote{EmotionNAS}. Specifically, we take two-stream features (i.e., handcrafted and deep features) as the inputs, followed by NAS to search for the optimal structure for each stream. Furthermore, we incorporate complementary information in different streams through an efficient information supplement module. Experimental results demonstrate that our method outperforms existing manually-designed and NAS-based models, setting the new state-of-the-art record.