Show HN: Alsa_rnnoise – RNNoise-based noise removal plugin for ALSA

Re:Show HN: Alsa_rnnoise – RNNoise-based noise removal plugi... by pabs3 on Sunday January 31, 2021 @08:16AM (#25978566)

Any idea about the license for the original data?

[ Parent | on HN ]

Re:Show HN: Alsa_rnnoise – RNNoise-based noise removal plugi... by pabs3 on Sunday January 31, 2021 @08:30AM (#25978667)

The paper links to the McGill TSP speech database (English & French) as one of the sources of the data, which claims to be BSD licensed:

http://www-mmsp.ece.mcgill.ca/Documents/Data/

[ Parent | on HN ]

Re:Show HN: Alsa_rnnoise – RNNoise-based noise removal plugi... by pabs3 on Sunday January 31, 2021 @08:32AM (#25978681)

The other source of data mentioned in the paper is the NTT Multi-Lingual Speech Database for Telephonometry, which seems to be commercial, so presumably under a proprietary license.

https://www.ntt-at.com/product/multilingual/ https://www.ntt-at.com/product/speech2002/

[ Parent | on HN ]

Re:Show HN: Alsa_rnnoise – RNNoise-based noise removal plugi... by pabs3 on Sunday January 31, 2021 @08:41AM (#25978741)

Hmm, OTOH, the 6.4GB data tarball says that it is from contributors who responded to the demo and is licensed under CC0.

[ Parent | on HN ]

Re:Show HN: Alsa_rnnoise – RNNoise-based noise removal plugi... by ArsenArsen on Sunday January 31, 2021 @10:45AM (#25979590)

+1, that data is CC0, and I believe that's all the data that was used for training.

[ Parent | on HN ]

Re:Show HN: Alsa_rnnoise – RNNoise-based noise removal plugi... by jmvalin on Sunday January 31, 2021 @03:38PM (#25982345)

No, exactly none of that data was used for training. The training was done before the demo that was asking for noise contributions. The contributions are CC0, but were never used (i.e. totally unknown dataset quality).

[ Parent | on HN ]

Re:Show HN: Alsa_rnnoise – RNNoise-based noise removal plugi... by the-dude on Sunday January 31, 2021 @09:50AM (#25979213)

So far we have 3 ideas!

[ Parent | on HN ]