Thu Jul 14 2022
Wed Jul 13 2022

Masked Autoencoders that Listen

Audio and speech analysis
Machine learning
Artificial Intelligence
Audio and speech analysis in business operations
Self-supervised representation learning from audio spectrograms

Audio-MAE sets new SotA on six audio and speech classification tasks, outperforming other recent models that use external supervised pre-training.

Audio-MAE can be used for self-supervised representation learning from audio spectrograms, providing better performance on audio and speech classification tasks. This approach can be implemented to optimize audio and speech analysis in business operations.

Re2G: Retrieve, Rerank, Generate

Natural language processing
Machine learning
Artificial Intelligence
Natural language processing in business operations
Text retrieval, reranking and generation

Large gains in four diverse tasks: zero-shot slot filling, question answering, fact checking and dialog, with relative gains of 9% to 34% over the previous SotA on the KILT leaderboard.

Re2G can be used for retrieval, reranking and generation of text, enhancing performance in tasks such as slot filling, question answering, fact checking, and dialog. This can be implemented in various businesses to optimize natural language processing.

Tue Jul 12 2022
Mon Jul 11 2022
Thu Jul 07 2022
Sun Jul 03 2022