@techreport{oai:ipsj.ixsq.nii.ac.jp:00224455,
 author = {Karen, Livescu and Ankita, Pasad and Ju-Chieh, Chou and Bowen, Shi and Karen, Livescu and Ankita, Pasad and Ju-Chieh, Chou and Bowen, Shi},
 issue = {58},
 month = {Feb},
 note = {Self-supervised speech representations have become ubiquitous in speech processing over the past few years. They have both improved the state of the art and made it feasible to learn speech models with very little labeled data.  However, it is not well understood what linguistic information is encoded in pre-trained models and how best to apply them to downstream tasks. In this talk I will describe recent work that begins to build an understanding of the layer-wise information learned by pre-trained speech models. We consider a number of popular pre-trained models and investigate the extent to which their layers encode spectral, phonetic, and word-level information. The results of these analyses also suggest some ways to improve or simplify the application of pre-trained models for downstream tasks., Self-supervised speech representations have become ubiquitous in speech processing over the past few years. They have both improved the state of the art and made it feasible to learn speech models with very little labeled data.  However, it is not well understood what linguistic information is encoded in pre-trained models and how best to apply them to downstream tasks. In this talk I will describe recent work that begins to build an understanding of the layer-wise information learned by pre-trained speech models. We consider a number of popular pre-trained models and investigate the extent to which their layers encode spectral, phonetic, and word-level information. The results of these analyses also suggest some ways to improve or simplify the application of pre-trained models for downstream tasks.},
 title = {What Do Self-Supervised Speech Representation Models Know?－A Layer-Wise Analysis－},
 year = {2023}
}