Enhanced Speech Emotion Recognition with Efficient Channel Attention Guided Deep CNN-BiLSTM Framework

TL;DR

This paper introduces a lightweight deep learning framework combining attention-based local and global features for speech emotion recognition, achieving state-of-the-art accuracy across multiple multilingual datasets.

Contribution

The paper proposes a novel CNN-BiLSTM architecture with integrated attention-based local feature blocks and a global feature block for efficient and accurate speech emotion recognition.

Findings

Achieved over 99% accuracy on TESS dataset.

Outperformed existing methods on five benchmark datasets.

Effectively captures complex emotional cues with reduced computational cost.

Abstract

Speech emotion recognition (SER) is crucial for enhancing affective computing and enriching the domain of human-computer interaction. However, the main challenge in SER lies in selecting relevant feature representations from speech signals with lower computational costs. In this paper, we propose a lightweight SER architecture that integrates attention-based local feature blocks (ALFBs) to capture high-level relevant feature vectors from speech signals. We also incorporate a global feature block (GFB) technique to capture sequential, global information and long-term dependencies in speech signals. By aggregating attention-based local and global contextual feature vectors, our model effectively captures the internal correlation between salient features that reflect complex human emotional cues. To evaluate our approach, we extracted four types of spectral features from speech audio samples: mel-frequency cepstral coefficients, mel-spectrogram, root mean square value, and zero-crossing rate. Through a 5-fold cross-validation strategy, we tested the proposed method on five multi-lingual standard benchmark datasets: TESS, RAVDESS, BanglaSER, SUBESCO, and Emo-DB, and obtained a mean accuracy of 99.65%, 94.88%, 98.12%, 97.94%, and 97.19% respectively. The results indicate that our model achieves state-of-the-art (SOTA) performance compared to most existing methods.