Analysis Of Speech Separation Performance Degradation On Emotional Speech Mixtures

Abstract

Despite recent strides made in Speech Separation, most models are trained on datasets with neutral emotions. Emotional speech has been known to degrade performance of models in a variety of speech tasks, which reduces the effectiveness of these models when deployed in real-world scenarios. In this paper we perform analysis to differentiate the performance degradation arising from the emotions in speech from the impact of out-of-domain inference. This is measured using a carefully designed test dataset, Emo2Mix, consisting of balanced data across all emotional combinations. We show that even models with strong out-of-domain performance such as Sepformer can still suffer significant degradation of up to 5.1 dB SI-SDRi on mixtures with strong emotions. This demonstrates the importance of accounting for emotions in real-world speech separation applications.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyip2023analysis

Related papers

• Analysis Of Impact Of Emotions On Target Speech Extraction And Speech Separation (2022)0.00
• Effect Of Different Splitting Criteria On The Performance Of Speech Emotion Recognition (2022)3.58
• Three-stage Speaker Verification Architecture In Emotional Talking Environments (2018)7.16
• Emomix: Emotion Mixing Via Diffusion Models For Emotional Speech Synthesis (2023)0.00
• Speech Emotion Recognition With Distilled Prosodic And Linguistic Affect Representations (2023)5.24
• How Speech Is Recognized To Be Emotional - A Study Based On Information Decomposition (2021)0.00
• Modeling Speech Emotion With Label Variance And Analyzing Performance Across Speakers And Unseen Acoustic Conditions (2025)0.00
• Decoding Emotions: A Comprehensive Multilingual Study Of Speech Models For Speech Emotion Recognition (2023)0.00