A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement

arXiv:2403.01369v1 Announce Type: cross
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 …

abstract arxiv automatic speech recognition closer look cs.ai cs.lg eess.as embeddings features found identification look recognition speaker speaker identification speech speech recognition systems tasks type utility wav2vec2