Abstract: Recent research has explored integrating lattice vector quantization (LVQ) into learned image compression models. Due to its more efficient Voronoi covering of vector space than scalar ...
Abstract: Neural speech and audio codecs have demonstrated decent quality of the decoded audio at low bitrates. They consist of three parts, an encoder, a decoder, and a quantizer. Residual vector ...
The output path must be a directory; it will be created if it does not exist. Input formats are auto-detected per file. Unsupported formats and write-only inputs (e.g., SVG) are skipped with a warning ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results