VCNAC: A Variable-Channel Neural Audio Codec for Mono, Stereo, and Surround Sound
On the map: Speech and audio language models → Vocoders and speech synthesis
Abstract (arXiv)
We present VCNAC, a variable channel neural audio codec. Our approach features a single encoder and decoder parametrization that enables native inference for different channel setups, from mono speech to cinematic 5.1 channel surround audio. Channel compatibility objectives ensure that multi-channel content maintains perceptual quality when decoded to fewer channels. The shared representation enables training of generative language models on a single set of codebooks while supporting inference-time scalability across modalities and channel configurations. Evaluation using objective spatial audio metrics and subjective listening tests demonstrates that our unified approach maintains high reconstruction quality across mono, stereo, and surround audio configurations.
Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models. Builds on 21 of its 29 references that are in the map. First posted on arXiv 21 Jan 2026.
Builds on
21 of 29 references.
Closest ancestors · 4
Same direction, newest first
- 2024Scaling Transformers for Low-Bitrate High-Quality Speech Coding29 Nov
- 2024SNAC: Multi-Scale Neural Audio Codec18 Oct
- 2023BANC: Towards Efficient Binaural Audio Neural Codec for Overlapping Speech14 Sep
- 2021SoundStream: An End-to-End Neural Audio Codec7 Jul
Other references · 17
- 2017Neural Discrete Representation Learningcited by 4,843
- 2022High Fidelity Neural Audio Compressioncited by 917
- 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 864
- 2023High-Fidelity Audio Compression with Improved RVQGANcited by 619
- 2023Simple and Controllable Music Generationcited by 540
- 2016FMA: A Dataset For Music Analysiscited by 234
- 2024Stable Audio Opencited by 203
- 2024Fast Timing-Conditioned Latent Audio Diffusioncited by 188
- 2024Restructuring Vector Quantization with the Rotation Trickcited by 54
- 2024Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Modelscited by 34
- 2025SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generationcited by 33
- 2023Controllable Music Production with Diffusion Models and Guidance Gradientscited by 30
5 more
- 2024Binaural Speech Enhancement Using Deep Complex Convolutional Transformer Networkscited by 13
- 2025SpectroStream: A Versatile Neural Codec for General Audiocited by 7
- 2025Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decodingcited by 6
- 2021A Training Framework for Stereo-Aware Speech Enhancement using Deep Neural Networkscited by 2
- 2023SpatialCodec: Neural Spatial Speech Codingcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook
- 2025BSCodec: A Band-Split Neural Codec for High-Quality Universal Audio Reconstruction
- 2026HARP: Harmonic-Aware Residual Partitioning for Neural Audio Codecs
- 2025Towards Evaluating Generative Audio: Insights from Neural Audio Codec Embedding Distances
- 2024Learning Source Disentanglement in Neural Audio Codec
- 2026OmniCodec: Low Frame Rate Universal Audio Codec with Semantic-Acoustic Disentanglement
- 2024Gull: A Generative Multifunctional Audio Codec
- 2025DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners