On The Behavior Of Intrusive And Non-intrusive Speech Enhancement Metrics In Predictive And Generative Settings

Abstract

Since its inception, the field of deep speech enhancement has been dominated by predictive (discriminative) approaches, such as spectral mapping or masking. Recently, however, novel generative approaches have been applied to speech enhancement, attaining good denoising performance with high subjective quality scores. At the same time, advances in deep learning also allowed for the creation of neural network-based metrics, which have desirable traits such as being able to work without a reference (non-intrusively). Since generatively enhanced speech tends to exhibit radically different residual distortions, its evaluation using instrumental speech metrics may behave differently compared to predictively enhanced speech. In this paper, we evaluate the performance of the same speech enhancement backbone trained under predictive and generative paradigms on a variety of metrics and show that intrusive and non-intrusive measures correlate differently for each paradigm. This analysis motivates

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydeoliveira2023on

Related papers

• Imetricgan: Intelligibility Enhancement For Speech-in-noise Using Generative Adversarial Network-based Metric Learning (2020)9.41
• Multi-cmgan+/+: Leveraging Multi-objective Speech Quality Metric Prediction For Speech Enhancement (2023)0.00
• Multi-metric Optimization Using Generative Adversarial Networks For Near-end Speech Intelligibility Enhancement (2021)8.60
• Metricnet: Towards Improved Modeling For Non-intrusive Speech Quality Assessment (2021)0.00
• Metricgan-u: Unsupervised Speech Enhancement/ Dereverberation Based Only On Noisy/ Reverberated Speech (2021)11.67
• Investigating Training Objectives For Generative Speech Enhancement (2024)9.76
• Metricgan: Generative Adversarial Networks Based Black-box Metric Scores Optimization For Speech Enhancement (2019)0.00
• CMGAN: Conformer-based Metric-gan For Monaural Speech Enhancement (2022)14.80