Hacker News with Generative AI: Audio Compression

Toward a Sparse and Interpretable Audio Codec (arxiv.org)
Most widely-used modern audio codecs, such as Ogg Vorbis and MP3, as well as more recent "neural" codecs like Meta's Encodec or the Descript Audio Codec are based on block-coding; audio is divided into overlapping, fixed-size "frames" which are then compressed.
Audio Compression, Machine Learning, Artificial Intelligence, Codecs
35 points by cochlear 47 days ago | 2 comments
FLAC 1.5 Delivers Multi-Threaded Encoding (phoronix.com)
FLAC 1.5 is out today as the newest feature update to the software built around the Free Lossless Audio Codec.
Audio Compression, Software, New Releases
220 points by mikece 137 days ago | 69 comments
Toward a Sparse Interpretable Audio Codec (cochlea.xyz)
Most widely-used modern audio codecs, such as Ogg Vorbis and MP3, as well as more recent "neural" codecs like Meta's Encodec or Descript's are based on block-coding; audio is divided into overlapping, fixed-size "frames" which are then compressed. While they produce excellent reproduction quality and can be used for downstream tasks such as text-to-audio, they do not produce an intuitive, directly-interpretable representation.
Audio Compression, Machine Learning, AI, Open Source
19 points by cochlear 150 days ago | 2 comments
MLow: Meta's low bitrate audio codec (engineering.fb.com)
Audio Compression, Meta, AI, Machine Learning
572 points by mikece 380 days ago | 197 comments
Zimtohrli: A New Psychoacoustic Perceptual Metric for Audio Compression (github.com/google)
Audio Compression, Software, Artificial Intelligence, Sound Engineering, Research
95 points by judiisis 416 days ago | 26 comments