Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques
It addresses the gap between in-lab SER research and real-world applications by focusing on ASR transcripts, which is incremental but important for practical deployment.
This study benchmarks Speech Emotion Recognition (SER) performance using ASR transcripts with varying Word Error Rates across three corpora, and proposes a unified framework that achieves lower WER and higher SER results compared to the best-performing ASR transcript.
Text data is commonly utilized as a primary input to enhance Speech Emotion Recognition (SER) performance and reliability. However, the reliance on human-transcribed text in most studies impedes the development of practical SER systems, creating a gap between in-lab research and real-world scenarios where Automatic Speech Recognition (ASR) serves as the text source. Hence, this study benchmarks SER performance using ASR transcripts with varying Word Error Rates (WERs) from eleven models on three well-known corpora: IEMOCAP, CMU-MOSI, and MSP-Podcast. Our evaluation includes both text-only and bimodal SER with six fusion techniques, aiming for a comprehensive analysis that uncovers novel findings and challenges faced by current SER research. Additionally, we propose a unified ASR error-robust framework integrating ASR error correction and modality-gated fusion, achieving lower WER and higher SER results compared to the best-performing ASR transcript. These findings provide insights into SER with ASR assistance, especially for real-world applications.