The reviewed record of science sign in
Pith

arxiv: 2408.16532 · v3 · pith:O26T7HA6 · submitted 2024-08-29 · eess.AS · cs.LG· cs.MM· cs.SD· eess.SP

WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:O26T7HA6record.jsonopen to challenge →

classification eess.AS cs.LGcs.MMcs.SDeess.SP
keywords modelswavtokenizeraudiocodecdiscretetokensacousticimproved
0
0 comments X
read the original abstract

Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into lower-dimensional discrete tokens. In this paper, we introduce WavTokenizer, which offers several advantages over previous SOTA acoustic codec models in the audio domain: 1)extreme compression. By compressing the layers of quantizers and the temporal dimension of the discrete codec, one-second audio of 24kHz sampling rate requires only a single quantizer with 40 or 75 tokens. 2)improved subjective quality. Despite the reduced number of tokens, WavTokenizer achieves state-of-the-art reconstruction quality with outstanding UTMOS scores and inherently contains richer semantic information. Specifically, we achieve these results by designing a broader VQ space, extended contextual windows, and improved attention networks, as well as introducing a powerful multi-scale discriminator and an inverse Fourier transform structure. We conducted extensive reconstruction experiments in the domains of speech, audio, and music. WavTokenizer exhibited strong performance across various objective and subjective metrics compared to state-of-the-art models. We also tested semantic information, VQ utilization, and adaptability to generative models. Comprehensive ablation studies confirm the necessity of each module in WavTokenizer. The related code, demos, and pre-trained models are available at https://github.com/jishengpeng/WavTokenizer.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 26 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model

    cs.SD 2026-06 unverdicted novelty 7.0

    FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates l...

  2. DTM-Codec: Dynamic Token Masking for VFR Speech Coding with Efficient Boundary Selection

    eess.AS 2026-06 unverdicted novelty 7.0

    DTM-Codec achieves better reconstruction quality and intelligibility than fixed-frame-rate neural speech codecs at matched total bitrate via dynamic token masking and Path Length Equalization for variable frame rates.

  3. Codec-Robust Attacks on Audio LLMs

    cs.SD 2026-05 unverdicted novelty 7.0

    CodecAttack perturbs audio in codec latent space with multi-bitrate EoT to achieve 85.5% average ASR on Opus-compressed Audio LLMs versus under 26% for waveform baselines, with transfer to MP3 and AAC.

  4. AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling

    cs.SD 2026-05 unverdicted novelty 7.0

    AffectCodec is an emotion-guided neural speech codec that preserves emotional cues during quantization while maintaining semantic fidelity and prosodic naturalness.

  5. PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization

    cs.LG 2026-05 unverdicted novelty 7.0

    PairAlign learns compact audio token sequences via self-alignment of paired content views using an autoregressive decoder, achieving strong cross-view consistency and edit-distance preservation while reducing token co...

  6. PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization

    cs.LG 2026-05 unverdicted novelty 7.0

    PairAlign learns compact variable-length token sequences for audio via self-alignment on paired content-preserving views, achieving 55% fewer archive tokens than VQ while preserving edit-distance retrieval at 12.71 tokens/s.

  7. Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM

    cs.CL 2026-05 unverdicted novelty 7.0

    TextPro-SLM minimizes the speech-text modality gap from the input side via a prosody-aware unified encoder, delivering the lowest gap and strong performance at 3B/7B scales with only ~1000 hours of audio.

  8. SPG-Codec: Exploring the Role and Boundaries of Semantic Priors in Ultra-Low-Bitrate Neural Speech Coding

    eess.AS 2026-04 unverdicted novelty 7.0

    Semantic priors from HuBERT and Whisper improve speech codec intelligibility up to 6 kbps but show diminishing returns beyond that, with a bitrate-aware regulation strategy balancing semantic consistency and naturalness.

  9. AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation

    cs.CV 2026-06 unverdicted novelty 6.0

    AVTok is a unified tokenizer that converts audio-video pairs into a compact 1D latent representation via dual-stream transformer and hierarchical training for improved reconstruction and cross-modal generation.

  10. Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment

    cs.SD 2026-06 unverdicted novelty 6.0

    Self-guidance adds a lightweight feature-mapping loss to align decoder manifolds in VQ-VAE speech codecs, raising reconstruction metrics and allowing 4x codebook reduction with no fidelity loss.

  11. dots.tts Technical Report

    cs.SD 2026-06 unverdicted novelty 6.0

    dots.tts reports SOTA benchmark results on Seed-TTS-Eval and other tests via continuous latent-space autoregressive modeling with three listed innovations and code release.

  12. SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue

    eess.AS 2026-05 unverdicted novelty 6.0

    SwanVoice is a zero-shot TTS system for 1-4 speakers that reports higher richness and hierarchy scores than open-source baselines on monologue and dialogue tasks via mixed training and DiffusionNFT post-training.

  13. AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

    cs.CV 2026-05 unverdicted novelty 6.0

    AnyMo is a masked-modeling framework for any-modality human motion generation trained on the new OmniHuMo dataset of 5,000+ hours of multimodal motion sequences.

  14. Codec-Robust Attacks on Audio LLMs

    cs.SD 2026-05 unverdicted novelty 6.0

    CodecAttack optimizes perturbations in neural audio codec latent space to reach 85.5% average target-substring ASR on compressed Opus audio while waveform baselines stay below 26%.

  15. Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse

    cs.LG 2026-05 unverdicted novelty 6.0

    A warm-up phase training VQ-VAEs as autoencoders first avoids dimensional collapse and yields better reconstruction and perceptual quality.

  16. Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse

    cs.LG 2026-05 unverdicted novelty 6.0

    An initial continuous autoencoder training phase prevents dimensional collapse in VQ-VAEs and yields lower reconstruction and perceptual losses.

  17. Two-Dimensional Quantization for Geometry-Aware Audio Coding

    cs.SD 2025-12 unverdicted novelty 6.0

    Q2D2 uses 2D geometric grid projections to quantize feature pairs in neural audio codecs, yielding implicit codebooks that improve efficiency and utilization over RVQ, VQ, and FSQ while maintaining reconstruction quality.

  18. Step-Audio 2 Technical Report

    cs.CL 2025-07 unverdicted novelty 6.0

    Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and c...

  19. SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization

    cs.SD 2025-05 unverdicted novelty 6.0

    SwitchCodec introduces Residual Experts Vector Quantization and a multi-tiered STFT discriminator to achieve PESQ 2.87 and ViSQOL 4.27 at 2.67 kbps while halving training time via post-training.

  20. GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot

    cs.CL 2024-12 conditional novelty 6.0

    GLM-4-Voice builds an end-to-end spoken chatbot by deriving a 175bps single-codebook tokenizer from ASR, synthesizing interleaved speech-text data, and continuing pre-training of GLM-4-9B on up to 1 trillion tokens be...

  21. Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals

    eess.AS 2026-05 unverdicted novelty 5.0

    A continuous-token model with shared Haar wavelet coefficients reports 39.92 dB audio, 29.37 dB image, and 23.93 dB video PSNR on three datasets and shows energy-based selection outperforms uniform selection by roughly 16 dB.

  22. Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM

    cs.CL 2026-05 unverdicted novelty 5.0

    TextPro-SLM reduces the speech-text modality gap by feeding an LLM backbone with synchronized text tokens and prosody embeddings from WhisperPro, achieving lowest gap scores at 3B/7B scales with roughly 1,000 hours of audio.

  23. Enhancing Speech Large Language Models through Reinforced Behavior Alignment

    cs.CL 2025-08 unverdicted novelty 5.0

    Reinforced Behavior Alignment (RBA) uses self-synthesized data from a teacher LLM and reinforcement learning to close the instruction-following gap in SpeechLMs, outperforming distillation and reaching SOTA on spoken ...

  24. Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer

    eess.AS 2026-05 unverdicted novelty 4.0

    SwanSphere introduces a causal autoregressive diffusion transformer architecture with SVAC contrastive learning and ODPO optimization for streaming spatial audio generation from video and text.

  25. Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents

    cs.CL 2026-05 unverdicted novelty 4.0

    Audio language models are benchmarked on five semantic and paralinguistic reasoning tasks to reveal limitations in handling spoken audio evidence, accent variation, and domain shifts.

  26. From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning

    eess.AS 2026-07 unverdicted novelty 3.0

    A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.