SoundStream: An End-to-End Neural Audio Codec · HackerPapers discussions

SoundStream: An End-to-End Neural Audio Codec — mentioned by sdenton4

Mon, 07 Jul 2025 21:13:16 GMT

VAE objectives are useful for pushing embeddings into a Gaussian distribution. Here's some work on low-latency neural compression that you might find interesting: https://arxiv.org/abs/2107.03312

Paper and discussion history. A mention is not an endorsement.

SoundStream: An End-to-End Neural Audio Codec — mentioned by cbhl

Wed, 16 Aug 2023 20:27:51 GMT

The author, Fabrice Bellard, is well-known for his work on QEMU (among other things), but I'd treat the rest of the posts as "idea sharing" at an early stage. For example, while BPG (Better Portable Graphics) didn't take off, the core idea (image formats based on video codecs) can be found in WebP (VP8, VP9) and AVIF (AV1) and HEIF (HEVC/H.265). For this, I'd look at comparable work in the audio codec space, including Lyra (https://arxiv.org/abs/2102.09660) and SoundStream (https://arxiv.org/abs/2107.03312). For text compression, I think it would be novel if you could get a lossy but…

Paper and discussion history. A mention is not an endorsement.

SoundStream: An End-to-End Neural Audio Codec — mentioned by sdenton4

Sun, 06 Feb 2022 17:29:29 GMT

The GANs are backdooring their way into really interesting outcomes, though. They're fantastic for compression: You compress the hell out of an input image or audio, then use the compressed features as conditioning for the GAN. This works great for super-resolution on images and speech compression. eg, for speech compression: https://arxiv.org/abs/2107.03312

Paper and discussion history. A mention is not an endorsement.