Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks

Explore this paper's citation graph

Summary

Experiments show that the proposed improved self-supervised method can learn transferable, robust, and problem-agnostic features that carry on relevant information from the speech signal, such as speaker identity, phonemes, and even higher-level features such as emotional cues.

Type
preprint
Published
2019-04-06
Cited by
260
References
46
Access
Open access

Keywords

Computer science, Encoder, Discriminator, Artificial intelligence, Speech recognition

References

Cited by

Related papers