mlsanityData to 14 Oct 2026

BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec

arXiv 2409.05377 ↗First posted 9 Sep 2024eess.AS cs.SDcited by 46

Not on the map. Why?

Abstract (arXiv)

We present BigCodec, a low-bitrate neural speech codec. While recent neural speech codecs have shown impressive progress, their performance significantly deteriorates at low bitrates (around 1 kbps). Although a low bitrate inherently restricts performance, other factors, such as model capacity, also hinder further improvements. To address this problem, we scale up the model size to 159M parameters that is more than 10 times larger than popular codecs with about 10M parameters. Besides, we integrate sequential models into traditional convolutional architectures to better capture temporal dependency and adopt low-dimensional vector quantization to ensure a high code utilization. Comprehensive objective and subjective evaluations show that BigCodec, with a bitrate of 1.04 kbps, significantly outperforms several existing low-bitrate codecs. Furthermore, BigCodec achieves objective performance comparable to popular codecs operating at 4-6 times higher bitrates, and even delivers better subjective perceptual quality than the ground truth.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Sep 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 22; 2026: 22.

46 papers.

Sort:

By area:

  1. 2025On The Landscape of Spoken Language Models: A Comprehensive Surveycited by 118
  2. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 113
  3. 2025Step-Audio 2 Technical Reportcited by 105
  4. 2024WavChat: A Survey of Spoken Dialogue Modelscited by 90
  5. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 70
  6. 2025MiMo-Audio: Audio Language Models are Few-Shot Learnerscited by 65
  7. 2025Recent Advances in Discrete Speech Tokens: A Reviewcited by 43
  8. 2025XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecscited by 23
  9. 2025FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networkscited by 18
  10. 2025Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representationcited by 17
  11. 2025TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modelingcited by 16
  12. 2026MOSS-TTS Technical Reportcited by 14
34 more
  1. 2025TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modelingcited by 13
  2. 2025FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillationcited by 9
  3. 2025MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generationcited by 7
  4. 2026UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Modelscited by 6
  5. 2024DM-Codec: Distilling Multimodal Representations for Speech Tokenizationcited by 5
  6. 2025SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codeccited by 5
  7. 2026Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenizationcited by 4
  8. 2025TTS-1 Technical Reportcited by 3
  9. 2026LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Spacecited by 3
  10. 2025UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic informationcited by 2
  11. 2025Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-ratescited by 2
  12. 2026UniSRCodec: Unified and Low-Bitrate Single Codebook Codec with Sub-Band Reconstructioncited by 2
  13. 2026Scaling Speech Tokenizers with Diffusion Autoencoderscited by 2
  14. 2026Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codeccited by 2
  15. 2025Eliminating stability hallucinations in llm-based tts models via attention guidancecited by 1
  16. 2025U-Codec: Ultra Low Frame-rate Neural Speech Codec for Fast High-fidelity Speech Generationcited by 1
  17. 2026The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecscited by 1
  18. 2026TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modelingcited by 1
  19. 2026MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corporacited by 1
  20. 2026Exploring Token-Space Manipulation in Latent Audio Tokenizerscited by 1
  21. 2026From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animationcited by 1
  22. 2026Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditionscited by 1
  23. 2025FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecscited by 0
  24. 2025Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditionscited by 0
  25. 2025Two-Dimensional Quantization for Geometry-Aware Audio Codingcited by 0
  26. 2026Absorbing Discrete Diffusion for Speech Enhancementcited by 0
  27. 2026Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignmentcited by 0
  28. 2026Probing Low Frame Rate Degradation in Neural Audio Codecscited by 0
  29. 2026HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Modelscited by 0
  30. 2026ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Modelscited by 0
  31. 2026Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenizationcited by 0
  32. 2026ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Codingcited by 0
  33. 2026TokenMapper: A Step Toward Interoperable Speech Token Translationcited by 0
  34. 2026BridgeCodec: Mamba Enhanced Neural Audio Codec with Schr"odinger Bridge at Low Bitratecited by 0