@zineblahrichi.bsky.social
🔉New paper out!
Recent audio codecs typically learn compression and quantization jointly, limiting the choice of quantization layers, which are non-differentiable by definition.
What if we used powerful neural quantizers like Qinco2 and trained them offline?
👉🏻 Read more: arxiv.org/abs/2503.19597
Recent audio codecs typically learn compression and quantization jointly, limiting the choice of quantization layers, which are non-differentiable by definition.
What if we used powerful neural quantizers like Qinco2 and trained them offline?
👉🏻 Read more: arxiv.org/abs/2503.19597
QINCODEC: Neural Audio Compression with Implicit Neural Codebooks
Neural audio codecs, neural networks which compress a waveform into discrete tokens, play a crucial role in the recent development of audio generative models. State-of-the-art codecs rely on the end-t...
arxiv.org
April 3, 2025 at 5:22 PM
🔉New paper out!
Recent audio codecs typically learn compression and quantization jointly, limiting the choice of quantization layers, which are non-differentiable by definition.
What if we used powerful neural quantizers like Qinco2 and trained them offline?
👉🏻 Read more: arxiv.org/abs/2503.19597
Recent audio codecs typically learn compression and quantization jointly, limiting the choice of quantization layers, which are non-differentiable by definition.
What if we used powerful neural quantizers like Qinco2 and trained them offline?
👉🏻 Read more: arxiv.org/abs/2503.19597