Being able to wirelessly connect headphones and speakers to your phone or computer is a magic many of us take for granted. It wasn't that long ago that the idea seemed impossibly futuristic. These ...

RepCodec is a speech tokenization method for converting a speech waveform into a sequence of discrete semantic tokens. The main idea is to train a representation codec which learns a vector ...

Abstract: The AV1 video compression format is developed by the Alliance for Open Media consortium. It achieves more than a 30% reduction in bit rate compared to its predecessor VP9 for the same ...

Abstract: Traditional video codecs follow the predictive coding architecture of motion-compensated prediction and residual transform coding. Inspired by recent advances in deep learning, we propose a ...

The Physical Sciences Directorate (PSD) conducts highly integrated basic and applied research programs that develop new materials, chemical processes, and technologies for energy generation and ...

Finally, the code for the web UI client used in the Moshi demo is provided in the client/ directory. If you want to fine tune Moshi, head out to kyutai-labs/moshi ...