Self-Supervised Learning Based Phone-Fortified Speech Enhancement

Qiu, Yuanhang; Wang, Ruili; Singh, Satwinder; Ma, Zhizhong; Feng, Huanqing

doi:10.21437/interspeech.2021-734

Search citation statements

Order By: Relevance

Paper Sections

Select...

Audio Ssl1

Model1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2023

Publication Types

Select...

Article2

Other2

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some very recent works, audio SSL approaches have been chosen to solve some special regression tasks related to SE 121 , 122 , 123 and source separation. 124 In Wang et al., 121 a pair of VAEs, named clean auto-encoder (CAE) and mixture auto-encoder (MAE), were exploited.…”

Section: Audio Sslmentioning

confidence: 99%

Audio self-supervised learning: A survey

Liu¹,

Mallol-Ragolta²,

Parada-Cabaleiro³

et al. 2022

Patterns

View full text Add to dashboard Cite

Section: Audio Sslmentioning

confidence: 99%

Audio self-supervised learning: A survey

Liu¹,

Mallol-Ragolta²,

Parada-Cabaleiro³

et al. 2022

Patterns

View full text Add to dashboard Cite

“…In some very recent works, audio SSL approaches have been specifically chosen to solve typically challenging tasks, such as speech enhancement [120]- [122] and source separation [123]. In [120], a pair of variational auto-encoders, named clean auto-encoder (CAE) and mixture autoencoder (MAE), were exploited.…”

Section: Modelmentioning

confidence: 99%

Audio Self-supervised Learning: A Survey

Liu¹,

Mallol-Ragolta²,

Parada-Cabeleiro³

et al. 2022

Preprint

View full text Add to dashboard Cite

Inspired by the humans' cognitive ability to generalise knowledge and skills, Self-Supervised Learning (SSL) targets at discovering general representations from large-scale data without requiring human annotations, which is an expensive and time consuming task. Its success in the fields of computer vision and natural language processing have prompted its recent adoption into the field of audio and speech processing. Comprehensive reviews summarising the knowledge in audio SSL are currently missing. To fill this gap, in the present work, we provide an overview of the SSL methods used for audio and speech processing applications. Herein, we also summarise the empirical works that exploit the audio modality in multimodal SSL frameworks, and the existing suitable benchmarks to evaluate the power of SSL in the computer audition domain. Finally, we discuss some open problems and point out the future directions on the development of audio SSL.

show abstract

Survey on deep learning in multimodal medical imaging for cancer detection

Tian,

Xu,

et al. 2023

Neural Comput & Applic

View full text Add to dashboard Cite

Self-Supervised Learning Based Phone-Fortified Speech Enhancement

Cited by 4 publications

References 0 publications

Audio self-supervised learning: A survey

Audio self-supervised learning: A survey

Audio Self-supervised Learning: A Survey

Survey on deep learning in multimodal medical imaging for cancer detection

Contact Info

Product

Resources

About