mlsanityData to 19 Oct 2026

VoCodec: An Efficient Lightweight Low-Bitrate Speech Codec

arXiv 2601.13055 ↗First posted 19 Jan 2026eess.AScited by 0

On the map: Speech and audio language models → Vocoders and speech synthesis

Abstract (arXiv)

Recent advancements in end-to-end neural speech codecs enable compressing audio at extremely low bitrates while maintaining high-fidelity reconstruction. Meanwhile, low computational complexity and low latency are crucial for real-time communication. In this paper, we propose VoCodec, a speech codec model featuring a computational complexity of only 349.29M multiply-accumulate operations per second (MACs/s) and a latency of 30 ms. With the competitive vocoder Vocos as its backbone, the proposed model ranked fourth on Track 1 in the 2025 LRAC Challenge and achieved the highest subjective evaluation score (MUSHRA) on the clean speech test set. Additionally, we cascade a lightweight neural network at the front end to extend its capability of speech enhancement. Experimental results demonstrate that the two systems achieve competitive performance across multiple evaluation metrics. Speech samples can be found at https://acceleration123.github.io/.

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 24 of its 30 references that are in the map. First posted on arXiv 19 Jan 2026.

Builds on

24 of 30 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Low-Resource Audio Codec (LRAC): 2025 Challenge Description27 Oct
  2. 2024BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec9 Sep
  3. 2024WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling29 Aug
  4. 2021SoundStream: An End-to-End Neural Audio Codec7 Jul

Other references · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,456
  2. 2017Neural Discrete Representation Learningcited by 4,843
  3. 2022A ConvNet for the 2020scited by 3,617
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,282
  5. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,462
  6. 2022High Fidelity Neural Audio Compressioncited by 917
  7. 2018SDR - half-baked or well done?cited by 626
  8. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 619
  9. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 552
  10. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 436
  11. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 218
  12. 2025Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Soundcited by 155
8 more
  1. 2021UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generationcited by 107
  2. 2025Recent Advances in Discrete Speech Tokens: A Reviewcited by 65
  3. 2024SCOREQ: Speech Quality Assessment with Contrastive Regressioncited by 49
  4. 2024MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Modelscited by 21
  5. 2025SHEET: A Multi-purpose Open-source Speech Human Evaluation Estimation Toolkitcited by 8
  6. 2024Crowdsourced Multilingual Speech Intelligibility Testingcited by 6
  7. 2025UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Searchcited by 4
  8. 2025Crowdsourcing MUSHRA Tests in the Age of Generative Speech Technologies: A Comparative Analysis of Subjective and Objective Testing Methodscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026VoCodec: A Low-bitrate Streamable Neural Speech Codec with Voicing-driven Quantization
  2. 2024ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers
  3. 2026ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding
  4. 2024Optimizing Neural Speech Codec for Low-Bitrate Compression via Multi-Scale Encoding
  5. 2025Baseline Systems For The 2025 Low-Resource Audio Codec Challenge
  6. 2024Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference
  7. 2026Ultra-Low-Bitrate Mel-Spectrogram-based Neural Speech Coding with Flow-Matching-based Refinement and Vocoding-driven Reconstruction ↗
  8. 2023AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec