mlsanityData to 14 Oct 2026

SpectroStream: A Versatile Neural Codec for General Audio

arXiv 2508.05207 ↗First posted 7 Aug 2025cs.SD cs.AI eess.AScited by 4

Not on the map. Why?

Abstract (arXiv)

We propose SpectroStream, a full-band multi-channel neural audio codec. Successor to the well-established SoundStream, SpectroStream extends its capability beyond 24 kHz monophonic audio and enables high-quality reconstruction of 48 kHz stereo music at bit rates of 4--16 kbps. This is accomplished with a new neural architecture that leverages audio representation in the time-frequency domain, which leads to better audio quality especially at higher sample rate. The model also uses a delayed-fusion strategy to handle multi-channel audio, which is crucial in balancing per-channel acoustic quality and cross-channel phase consistency.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

20 of 25 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Layer Normalizationcited by 5,669
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  4. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  5. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  6. 2022High Fidelity Neural Audio Compressioncited by 687
  7. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 616
  8. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  9. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 543
  10. 2023MusicLM: Generating Music From Textcited by 448
  11. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
  12. 2023SoundStorm: Efficient Parallel Audio Generationcited by 114
8 more
  1. 2020ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metriccited by 79
  2. 2020Wavesplit: End-to-End Speech Separation by Speaker Clusteringcited by 75
  3. 2020Streaming keyword spotting on mobile devicescited by 47
  4. 2020A Spectral Energy Distance for Parallel Speech Synthesiscited by 42
  5. 2020SEANet: A Multi-modal Speech Enhancement Networkcited by 37
  6. 2024MusicRL: Aligning Music Generation to Human Preferencescited by 32
  7. 2025FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networkscited by 18
  8. 2025FlowDec: A flow-based full-band general audio codec with high perceptual qualitycited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025SoundReactor: Frame-level Online Video-to-Audio Generationcited by 5
  2. 2026F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generationcited by 1
  3. 2026Taming Audio VAEs via Target-KL Regularizationcited by 0
  4. 2026Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Codingcited by 0