A Closer Look At Wav2vec2 Embeddings For On-device Single-channel Speech Enhancement

Abstract

Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech recognition and associated tasks, their utility in speech enhancement systems is yet to be firmly established, and perhaps not properly understood. In this paper, we investigate the uses of SSL representations for single-channel speech enhancement in challenging conditions and find that they add very little value for the enhancement task. Our constraints are designed around on-device real-time speech enhancement -- model is causal, the compute footprint is small. Additionally, we focus on low SNR conditions where such models struggle to provide good enhancement. In order to systematically examine how SSL representations impact performance of such enhancement models, we propose a variety of techniques to utilize these embeddings which include different for

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshankar2024a

Related papers

• Efficient Infusion Of Self-supervised Representations In Automatic Speech Recognition (2024)0.00
• Investigating Self-supervised Learning For Speech Enhancement And Separation (2022)13.44
• The Efficacy Of Self-supervised Speech Models For Audio Representations (2022)0.00
• An Adapter Based Pre-training For Efficient And Scalable Self-supervised Speech Representation Learning (2021)8.35
• Towards Supervised Performance On Speaker Verification With Self-supervised Learning By Leveraging Large-scale ASR Models (2024)7.50
• Non-contrastive Self-supervised Learning For Utterance-level Information Extraction From Speech (2022)9.59
• Exploiting Consistency-preserving Loss And Perceptual Contrast Stretching To Boost Ssl-based Speech Enhancement (2024)6.77
• Investigation Of Ensemble Features Of Self-supervised Pretrained Models For Automatic Speech Recognition (2022)9.41