Neural Audio Codecs

Ask about this topic

Overview

Neural audio codecs compress sound by mapping waveforms into compact latent representations, often using residual vector quantization, then reconstructing audio with a learned decoder. Current approaches balance perceptual fidelity with bitrate, intelligibility, speaker identity, and attributes such as emotion or pitch, using perceptual losses, self-supervised features, and separate semantic and acoustic streams. Researchers also design codec tokens for downstream generation with language models, while developing streaming codecs, variable frame rates, and hybrid discrete-continuous representations. A central challenge is that lower rates and more predictable tokens can lose acoustic detail, and quality metrics do not always reveal whether information needed for speech or other tasks survives compression.

Latest papers

CardsList

87 papers18 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

Jun 1, 2026

EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement

Audio tokenizers serve as the discrete interface between continuous audio and Audio Language Models (ALMs), but existing tokenizers often struggle to support both understanding and generation. Reconstruction-oriented codecs preserve acoustic fidelity but lack rich semantics, while semantic-aware tokenizers typically rely on separate semantic and acoustic streams, introducing redundancy or misalignment. We propose EntangleCodec, a unified discrete audio tokenizer that learns caption-aligned semantic-acoustic representations before quantization. By aligning audio with rich captions rather than ASR transcripts, EntangleCodec captures linguistic content, speaker identity, emotion, prosody, and acoustic scenes within a compact token stream. A flow-matching diffusion decoder further enables high-quality reconstruction across speech, music, and general audio. EntangleCodec achieves reconstruction quality competitive with specialized codecs, outperforms all codec-based baselines on audio understanding by up to +7.4% on MMAR, and supports both TTS and TTA generation in a unified framework. Furthermore, EntangleCodec-based audio language models demonstrate strong scaling behavior: even at 0.6B parameters, the model surpasses specialized continuous-representation LLMs with over 13B parameters across three benchmarks using \textbf{22×\times} fewer parameters; scaling to 8B further establishes new state-of-the-art results on MMAR, highlighting that representation quality is as critical as model scale in audio language modeling. Code and model weights are available at https://github.com/luckyerr/EntangleCodec.

Hui Li, Yangfan Gao, Junlin Shang +4

Fudan University

Audio Representation LearningNeural Audio CodecsAudio UnderstandingAudio-Language ModelsAudio TokenizationDiscrete Speech Representation Learning
AskPDF
May 22, 2026

AffectCodec: Emotion-Preserving Neural Speech Codec with Block-Diagonal Residual FSQ

Neural speech codecs have become the discrete interface between raw audio and speech language models, yet they remain optimized primarily for acoustic reconstruction fidelity, which leaves emotion-relevant cues vulnerable to being discarded during quantization, limiting the affective capacity of downstream models. We trace this degradation to two mechanisms: reconstruction-driven bit allocation under limited bitrate and cross-stream leakage in concatenation-based codecs, where acoustic gradients can overwrite nominally emotion-reserved dimensions. We propose AffectCodec, an emotion-preserving neural speech codec built on Block-Diagonal Residual Finite Scalar Quantization (BD-RFSQ). By imposing block-diagonal input and output projections over emotion and acoustic subspaces, BD-RFSQ transforms bit allocation from implicit and loss-driven to explicit and structurally guaranteed, while still preserving a flat token interface for downstream speech language models. AffectCodec further combines this structurally constrained quantizer with multi-granularity emotion conditioning and multi-rate training, enabling robust affect preservation at low bitrates. Experiments across multiple emotional speech benchmarks show that AffectCodec substantially improves emotion preservation, especially in the low-bitrate regime, while maintaining competitive acoustic quality and intelligibility. These results suggest that structurally protected quantization is an effective principle for preserving emotion-relevant information and may provide a general route toward attribute-aware neural speech compression.

Zhaoyang Meng, Zhengyao Ma, Kecan Mao +2

Beijing University of Posts and Telecommunications

Neural Audio CodecsNeural EncodingNeural Network QuantizationAffective Computing
AskPDF
May 19, 2026

Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning

In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 300 bit per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 4.64% WER on the LibriSpeech test-clean set at 300 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.55% on test-clean and 10.4% on test-other, corresponding to a 23% relative reduction while preserving perceptual quality.

Junyi Wang, Chi Zhang, Jing Qian +4

Tsinghua University, China · Huawei Technologies Co., Ltd, China

Neural Audio CodecsNeural Encoding
AskPDF
May 18, 2026

SAME: A Semantically-Aligned Music Autoencoder

Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio-codec autoencoder. In this work we introduce SAME (Semantically-Aligned Music autoEncoder), an autoencoder for stereo music and general audio that reaches a 4096×\times temporal compression ratio while maintaining reconstruction quality and downstream generative performance. We achieve this by combining a tranformer-based backbone with set of semantic regularisation approaches, phase-aware reconstruction losses and improved discriminator designs. The architecture delivers substantial computational cost benefits, through both its high compression ratio and its reliance on well-optimised transformer primitives. Two variants (a large SAME-L and a CPU-deployable SAME-S) are released in open-weights form.

Julian D. Parker, Zach Evans, CJ Carr +4

Stability AI

Audio Representation LearningNeural Audio CodecsAutoencoders
AskPDF
May 15, 2026

Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation

Autoregressive music generation depends strongly on the audio tokenizer. Existing high-fidelity codecs often use residual multi-codebook quantization, which preserves reconstruction quality but complicates language modeling after sequence flattening, as the residual hierarchy imposes strong sequential dependencies and can amplify error accumulation. We propose BandTok, a generation-oriented 2D Mel-spectrogram tokenizer that represents each frame with Mel-frequency band tokens from a single shared codebook. This design yields a physically interpretable time-frequency token grid with a more independent token structure, making it better suited for autoregressive modeling. BandTok improves reconstruction with a multi-scale PatchGAN objective and EMA codebook updates. We further introduce an autoregressive language model with 2D Rotary Position Embedding (2D RoPE) to preserve temporal and frequency-band structure during generation. Experiments show that BandTok improves over residual-codebook tokenizers and achieves strong results in a data-limited setting. The source code and generation demos for this work are publicly available.

Yuqing Cheng, Xingyu Ma, Guochen Yu +1

Department of Music AI and Information Technology, Central Conservatory of Music, Beijing, China · Zhipu AI, Beijing, China

Neural Audio CodecsAutoregressive Language ModelingAudio TokenizationMusic Generation
AskPDF
May 11, 2026

Exploring Token-Space Manipulation in Latent Audio Tokenizers

Neural audio codecs provide compact discrete representations for speech generation and manipulation. However, most codecs organize tokens as frame-level sequences, making it difficult to study or intervene on global factors of variation. In this work, we propose the Latent Audio Tokenizer for Token-space Editing (LATTE) that appends a fixed set of learnable latent tokens to the audio feature sequence and retains only these tokens for quantization and decoding. This design produces a compact, non-temporally aligned bottleneck in which each token can aggregate global information across the full utterance. We show that the resulting tokenizer preserves competitive reconstruction quality in low-bitrate speech coding settings while enabling simple token-space interventions. In particular, we find that swapping selected latent token positions between utterances can modify global attributes, such as speaker identity and background noise, and we evaluate these interventions on voice conversion and denoising tasks. Our results suggest that compact latent audio tokenizers can support controllable audio manipulation without supervision in task-specific editing models.

Francesco Paissan, Luca Della Libera, Mirco Ravanelli +1

1Mila – Québec AI Institute · 2Université Laval · 3Concordia University

Audio Representation LearningNeural Audio CodecsAudio EditingSpeech ProcessingSpeech EnhancementAudio Tokenization+1
AskPDF
May 11, 2026

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

Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acoustic reconstruction, leaving emotion expressiveness insufficiently modeled at the representation level. We propose an emotion-guided neural speech codec that explicitly preserves emotional information while maintaining semantic fidelity and prosodic naturalness. Our framework combines emotion-semantic guided latent modulation, relation-preserving emotional-semantic distillation, and emotion-weighted semantic alignment to retain emotionally salient cues under compression. Extensive evaluations across speech reconstruction, emotion recognition, and downstream text-to-speech generation demonstrate improved emotion consistency and perceptual quality without sacrificing content accuracy.

Jiacheng Shi, Hongfei Du, Xinyuan Song +3

College of William & Mary · Emory University · George Mason University

Audio Representation LearningNeural Audio CodecsNeural EncodingDiscrete Speech Representation Learning
AskPDF
May 11, 2026

Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs

Generating realistic drum audio directly from symbolic representations is a challenging task at the intersection of music perception and machine learning. We propose a system that transforms an expressive drum grid, a time-aligned MIDI representation with microtiming and velocity information, into drum audio by predicting discrete codes of a neural audio codec. Our approach uses a Transformer-based model to map the drum grid input to a sequence of codec tokens, which are then converted to waveform audio via a pre-trained codec decoder. We experiment with multiple state-of-the-art neural codecs, namely EnCodec, DAC, and X-Codec, to assess how the choice of audio representation impacts the quality of the generated drums. The system is trained and evaluated on the Expanded Groove MIDI Dataset, E-GMD, a large collection of human drum performances with paired MIDI and audio. We evaluate the fidelity and musical alignment of the generated audio using objective metrics. Overall, our results establish codec-token prediction as an effective route for drum grid-to-audio generation and provide practical insights into selecting audio tokenizers for percussive synthesis.

Konstantinos Soiledis, Maximos Kaliakatsos-Papakostas, Dimos Makris +1

Dept. of Music Technology and Acoustics, Hellenic Mediterranean University, Rethymno & Athens, Greece · Athena RC, Athens, Greece

Neural Audio CodecsMusic GenerationAudio Generation
AskPDF
Apr 20, 2026

LLM-Codec: Neural Audio Codec Meets Language Model Objectives

Neural audio codecs are widely used as tokenizers for spoken language models, but they are optimized for waveform reconstruction rather than autoregressive prediction. This mismatch injects acoustically driven uncertainty into the discrete token space and increases language-model perplexity. We propose \ours, which augments codec training with language-model-facing objectives while keeping both codec and LLM architectures unchanged. \ours introduces (i) future token prediction with Medusa-style multi-step heads to encourage multi-step predictability, and (ii) semantic alignment that matches audio and text representations via a memory-bank contrastive loss. A differentiable Gumbel bridge enables end-to-end gradients from these objectives to the codec encoder. On SALMon speech coherence, token LMs trained on \ours reach 61.6% accuracy (+12.1 points over AUV) while reducing perplexity 35. On Codec-SUPERB-tiny, \ours improves speech Mel distance by 5.0% over AUV while simultaneously achieving the learnability gains, demonstrating that reconstruction fidelity and token predictability can be improved together.

Ho-Lam Chung, Yiming Chen, Hung-yi Lee

Graduate Institute of Communication Engineering, National Taiwan University · ASUS Intelligent Cloud Services · NTU Artificial Intelligence Center of Research Excellence (NTU AI-CoRE)

Neural Audio CodecsMulti-Token PredictionNext-Token PredictionAudio TokenizationSpeech Language ModelsDiscrete Speech Representation Learning
AskPDF
Apr 16, 2026

ClariCodec: Optimising Neural Speech Codes for 200bps Communication using Reinforcement Learning

In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 200 bit per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 3.68% WER on the LibriSpeech test-clean set at 200 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.20% on test-clean and 8.93% on test-other, corresponding to a 13% relative reduction while preserving perceptual quality.

Junyi Wang, Chi Zhang, Jing Qian +4

Tsinghua University, China · Huawei Technologies Co., Ltd, China

Neural Audio CodecsSpeech ProcessingNeural Encoding
AskPDF
Mar 18, 2026

Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: A Case Study on Accent Information

Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretability of NAC representations is critical for understanding and deploying them in sensitive applications. Hence, we employ Sparse Autoencoders (SAEs) to decompose dense NAC representations into sparse, interpretable activations. In this work, we focus on a challenging paralinguistic attribute-accent-and propose a framework to quantify NAC interpretability. We evaluate four NAC models under 16 SAE configurations using a relative performance index. Our results show that DAC and SpeechTokenizer achieve the highest interpretability. We further reveal that acoustic-oriented NACs encode accent information primarily in activation magnitudes of sparse representations, whereas phonetic-oriented NACs rely more on activation positions, and that low-bitrate EnCodec variants show higher interpretability.

Shih-Heng Wang, Tiantian Feng, Aditya Kommineni +4

University of Southern California, USA

Neural Audio CodecsSparse AutoencodersNeural Network InterpretabilityNeural Encoding
AskPDF
Mar 15, 2026

CodecMOS-Accent: A MOS Benchmark of Resynthesized and TTS Speech from Neural Codecs Across English Accents

We present the CodecMOS-Accent dataset, a mean opinion score (MOS) benchmark designed to evaluate neural audio codec (NAC) models and the large language model (LLM)-based text-to-speech (TTS) models trained upon them, especially across non-standard speech like accented speech. The dataset comprises 4,000 codec resynthesis and TTS samples from 24 systems, featuring 32 speakers spanning ten accents. A large-scale subjective test was conducted to collect 19,600 annotations from 25 listeners across three dimensions: naturalness, speaker similarity, and accent similarity. This dataset does not only represent an up-to-date study of recent speech synthesis system performance but reveals insights including a tight relationship between speaker and accent similarity, the predictive power of objective metrics, and a perceptual bias when listeners share the same accent with the speaker. This dataset is expected to foster research on more human-centric evaluation for NAC and accented TTS.

Wen-Chin Huang, Nicholas Sanders, Erica Cooper

Nagoya University, Japan · University of Edinburgh, United Kingdom · National Institute Of Information And Communications Technology, Japan

TTS EvaluationSpeech Quality AssessmentNeural Audio Codecs
AskPDF
Mar 14, 2026

Probing neural audio codecs for distinctions among English nuclear tunes

State-of-the-art spoken dialogue models (Défossez et al. 2024; Schalkwyk et al. 2025) use neural audio codecs to "tokenize" audio signals into a lower-frequency stream of vectorial latent representations, each quantized using a hierarchy of vector codebooks. A transformer layer allows these representations to reflect some time- and context-dependent patterns. We train probes on labeled audio data from Cole et al. (2023) to test whether the pitch trajectories that characterize English phrase-final (nuclear) intonational tunes are among these patterns. Results: Linear probes trained on the unquantized latents or some of the associated codewords yield above-chance accuracy in distinguishing eight phonologically specified nuclear tunes with monotonal pitch accents (top average test accuracy (TATA): 0.31) and the five clusters of these tunes that are robust in human speech production and perception (TATA: 0.45). Greater accuracy (TATAs: 0.74-0.89) is attained for binary distinctions between classes of rising vs. falling tunes, respectively used for questions and assertions. Information about tunes is spread among all codebooks, which calls into question a distinction between 'semantic' and 'acoustic' codebooks found in the literature. Accuracies improve with nonlinear probes, but discrimination among the five clusters remains far from human performance, suggesting a fundamental limitation of current codecs.

Juan Pablo Vigneaux, Jennifer Cole

Northwestern University

Speech ProsodyNeural Audio CodecsAudio Representation Learning
AskPDF
Mar 11, 2026

Speech Codec Probing from Semantic and Phonetic Perspectives

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation tasks. However, emerging evidence suggests that the term "semantic" in speech processing does not align with linguistic lexical-semantic, leading to a mismatch between speech and text modality. In this paper, we systematically analyze the information encoded by several widely used speech tokenizers, evaluating their lexical-semantic and phonetic content through three tasks. Our results show that current tokenizers primarily capture phonetic rather than lexical-semantic structure, deriving practical implications for the design of next-generation speech tokenization methods. Code is released to public at https://github.com/Alexuan/codec_probing_release.

Xuan Shi, Chang Zeng, Tiantian Feng +3

University of Southern California, USA · Dolby Laboratories, USA

Audio Representation LearningNeural Audio CodecsSpeech ProcessingAudio Tokenization
AskPDF
Mar 10, 2026

Attack-Dependent Robustness of Neural Audio Codecs for Adversarial ASR

Neural audio codecs impose a discrete bottleneck through residual vector quantization (RVQ), making them a useful class of inference-time transformations for reducing adversarial perturbations before ASR inference. We study how codec quantization depth affects defended ASR under non-adaptive, standard adaptive, and quantization-aware adaptive untargeted ℓ∞\ell_\infty attacks. Under non-adaptive attacks, intermediate RVQ depths yield the lowest word error rates and outperform traditional compression at comparable bitrates. However, this apparent optimum is not stable under adaptive evaluation. The standard identity-gradient adaptive baseline (BPDA+EOT) can overestimate robustness, while an implementation of an RVQ-relaxed adaptive attack (SoftVQ-PGD) substantially changes the observed depth trend and largely removes the intermediate-depth advantage. Overall, neural codecs can improve defended ASR under specific threat models. However, the relationship between robustness and RVQ depth depends on the attack used for evaluation, rather than on the codec architecture alone.

Jordan Prescott, Thanathai Lertpetchpun, Shrikanth Narayanan

Signal Analysis and Interpretation Laboratory, University of Southern California, USA

ASR EvaluationNeural Audio CodecsResidual VQNeural Network RobustnessAutomatic Speech Recognition
AskPDF
Mar 6, 2026

StreamVoiceAnon+: Emotion-Preserving Streaming Speaker Anonymization via Frame-Level Acoustic Distillation

We address the challenge of preserving emotional content in streaming speaker anonymization (SA). Neural audio codec language models trained for audio continuation tend to degrade source emotion: content tokens discard emotional information, and the model defaults to dominant acoustic patterns rather than preserving paralinguistic attributes. We propose supervised finetuning with neutral-emotion utterance pairs from the same speaker, combined with frame-level emotion distillation on acoustic token hidden states. All modifications are confined to finetuning, which takes less than 2 hours on 4 GPUs and adds zero inference latency overhead, while maintaining a competitive 180ms streaming latency. On the VoicePrivacy 2024 protocol, our approach achieves a 49.2% UAR (emotion preservation) with 5.77% WER (intelligibility), a +24% relative UAR improvement over the baseline (39.7%->49.2%) and +10% over the emotion-prompt variant (44.6% UAR), while maintaining strong privacy (EER 49.0%). Demo and code are available: https://anonymous3842031239.github.io/

Nikita Kuzmin, Kong Aik Lee, Eng Siong Chng

Nanyang Technological University, Singapore · Institute for Infocomm Research (I2R), A*STAR, Singapore · The Hong Kong Polytechnic University, Hong Kong

Speaker AnonymizationPrivacy-Preserving Speech ProcessingNeural Audio Codecs
AskPDF
Mar 6, 2026

Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec

Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation improves encoded representations, it does not guarantee content preservation in reconstructed speech. In this work, we demonstrate that self-supervised representation reconstruction (SSRR) loss fundamentally improves codec training and performance. First, SSRR significantly accelerates convergence, enabling competitive results after 300k training steps on a single H200 GPU. Second, it enhances intelligibility by reconstructing distilled self-supervised representations from codec outputs. Third, SSRR enables high intelligibility without additional lookahead in streaming Transformer-based codecs, allowing a zero-lookahead architecture for real-time deployment. On LibriSpeech test-clean, JHCodec achieves the best WER and CER among the evaluated codecs while maintaining zero lookahead and low end-to-end latency. We open-source the full implementation, training pipeline, and demo on GitHubh ttps://github.com/jhcodec843/jhcodec.

Junhyeok Lee, Xiluo He, Jihwan Lee +6

Center for Language and Speech Processing, Johns Hopkins University, USA · Signal Analysis and Interpretation Laboratory, University of Southern California, USA

Neural Audio CodecsSelf-Supervised Learning
AskPDF
Mar 2, 2026

CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space

Speech Bandwidth Extension improves clarity and intelligibility by restoring/inferring appropriate high-frequency content for low-bandwidth speech. Existing methods often rely on spectrogram or waveform modeling, which can incur higher computational cost and have limited high-frequency fidelity. Neural audio codecs offer compact latent representations that better preserve acoustic detail, yet accurately recovering high-resolution latent information remains challenging due to representation mismatch. We present CodecFlow, a neural codec-based BWE framework that performs efficient speech reconstruction in a compact latent space. CodecFlow employs a voicing-aware conditional flow converter on continuous codec embeddings and a structure-constrained residual vector quantizer to improve latent alignment stability. Optimized end-to-end, CodecFlow achieves strong spectral fidelity and enhanced perceptual quality on 8 kHz to 16 kHz and 44.1 kHz speech BWE tasks.

Bowen Zhang, Junchuan Zhao, Ian McLoughlin +2

Singapore Institute of Technology, Singapore · Nanyang Technological University, Singapore · National University of Singapore, Singapore

Speech EnhancementNeural Audio Codecs
AskPDF
Mar 2, 2026

TQCodec: Towards neural audio codec for high-fidelity music streaming

We propose TQCodec, a neural audio codec designed for high-bitrate, high-fidelity music streaming. Unlike existing neural codecs that primarily target ultra-low bitrates (<= 16kbps), TQCodec operates at 44.1 kHz and supports bitrates from 32 kbps to 128 kbps, aligning with the standard quality of modern music streaming platforms. The model adopts an encoder-decoder architecture based on SEANet for efficient on-device computation and introduces several enhancements: an imbalanced network design for improved quality with low overhead, SimVQ for mid-frequency detail preservation, and a phase-aware waveform loss. Additionally, we introduce a perception-driven band-wise bit allocation strategy to prioritize perceptually critical lower frequencies. Evaluations on diverse music datasets demonstrate that TQCodec achieves superior audio quality at target bitrates, making it well-suited for high-quality audio applications.

Lixing He, Zhouxuan Chen, Mingshuai Liu +6

Tencent Music Entertainment · The Chinese University of Hong Kong · Southeast University +1

Neural Audio CodecsRate-Distortion Optimization
AskPDF
Feb 18, 2026

How to Label Resynthesized Audio: The Dual Role of Neural Audio Codecs in Audio Deepfake Detection

Since Text-to-Speech systems typically don't produce waveforms directly, recent spoof detection studies use resynthesized waveforms from vocoders and neural audio codecs to simulate an attacker. Unlike vocoders, which are specifically designed for speech synthesis, neural audio codecs were originally developed for compressing audio for storage and transmission. However, their ability to discretize speech also sparked interest in language-modeling-based speech synthesis. Owing to this dual functionality, codec resynthesized data may be labeled as either bonafide or spoof. So far, very little research has addressed this issue. In this study, we present a challenging extension of the ASVspoof 5 dataset constructed for this purpose. We examine how different labeling choices affect detection performance and provide insights into labeling strategies.

Yixuan Xiao, Florian Lux, Alejandro Pérez-González-de-Martos +1

University of Stuttgart, Institute for Natural Language Processing, Germany · AppTek GmbH, Germany

Audio Deepfake DetectionASVspoofNeural Audio Codecs
AskPDF
Feb 17, 2026

A Generative-First Neural Audio Autoencoder

Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are reconstruction-first: they incur high latent rates, slow encoding, and separate architectures for discrete vs. continuous latents and for different audio channel formats, hindering workflows from preprocessing to inference conditioning. We introduce a generative-first architecture for audio autoencoding that increases temporal downsampling from 2048x to 3360x and supports continuous and discrete representations and common audio channel formats in one model. By balancing compression, quality, and speed, it delivers 10x faster encoding, 1.6x lower rates, and eliminates channel-format-specific variants while maintaining competitive reconstruction quality. This enables applications previously constrained by processing costs: a 60-second mono signal compresses to 788 tokens, making generative modeling more tractable.

Jonah Casebeer, Ge Zhu, Zhepei Wang +1

Adobe Research

AutoencodersAudio Representation LearningNeural Audio CodecsAudio Token Compression
AskPDF
Feb 17, 2026

The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs

Neural audio codecs (NACs) typically encode the short-term energy (gain) and normalized structure (shape) of speech/audio signals jointly within the same latent space. As a result, they are poorly robust to a global variation of the input signal level in the sense that such a variation has a strong influence on the embedding vectors at the output of the encoder and their quantization. This methodology is inherently inefficient, leading to codebook redundancy and suboptimal bitrate-distortion performance. To address these limitations, we propose to introduce shape-gain decomposition, widely used in classical speech and audio coding, into the NAC framework. The principle of the proposed Equalizer methodology, easily applicable to any NAC, is to decompose the input signal---before the NAC encoder---into gain and normalized shape vector on a short-term basis. The shape vector is processed by the NAC, while the gain is quantized with scalar quantization and transmitted separately. The output (decoded) signal is reconstructed from the normalized output of the NAC and the quantized gain. Our experiments conducted on speech signals with four different prominent codecs show that this general methodology enables a substantial gain in bitrate-distortion performance, as well as a massive reduction in quantizer complexity.

Samir Sadok, Laurent Girin, Xavier Alameda-Pineda

Inria at Univ. Grenoble Alpes, CNRS, LJK, France · Univ. Grenoble Alpes, Grenoble-INP, GIPSA-lab, France

Neural Audio CodecsRate-Distortion Optimization
AskPDF
Feb 16, 2026

S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization

Neural audio compression models have recently achieved extreme compression rates, enabling efficient latent generative modeling. Conversely, latent generative models have been applied to compression, pushing the limits of continuous and discrete approaches. However, existing methods remain constrained to low-resolution audio and degrade substantially at very low bitrates, where audible artifacts are prominent. In this paper, we present S-PRESSO, a 48kHz sound effect compression model that produces both continuous and discrete embeddings at ultra-low bitrates, down to 0.096 kbps, via offline quantization. Our model relies on a pretrained latent diffusion model to decode compressed audio embeddings learned by a latent encoder. Leveraging the generative priors of the diffusion decoder, we achieve extremely low frame rates, down to 1Hz (750x compression rate), producing convincing and realistic reconstructions at the cost of exact fidelity. Despite operating at high compression rates, we demonstrate that S-PRESSO outperforms both continuous and discrete baselines in audio quality, acoustic similarity and reconstruction metrics.

Zineb Lahrichi, Gaëtan Hadjeres, Gaël Richard +1

IP Paris, SonyAI · Sony AI · LTCI, Télécom Paris, Institut Polytechnique de Paris +2

Neural Audio CodecsAudio Token CompressionAudio Diffusion Models
AskPDF
Jan 15, 2026

HeartMuLa: A Family of Open Sourced Music Foundation Models

We present a family of open-source Music Foundation Models designed to advance large-scale music understanding and generation across diverse tasks and modalities. Our framework consists of four major components: (1) HeartCLAP, an audio-text alignment model; (2) HeartTranscriptor, a robust lyric recognition model optimized for real-world music scenarios; and (3) HeartCodec, a low-frame-rate (12.5 Hz) yet high-fidelity music codec tokenizer that captures long-range musical structure while preserving fine-grained acoustic details and enabling efficient autoregressive modeling; (4) HeartMuLa, an LLM-based song generation model capable of synthesizing high-fidelity music under rich, user-controllable conditions (e.g., textual style descriptions, lyrics, and reference audio). In addition, it provides two specialized modes: (i) fine-grained musical attribute control, which allows users to specify the style of different song sections (e.g., intro, verse, chorus) using natural language prompts; and (ii) short, engaging music generation, which is suitable as background music for short videos. Lastly, HeartMuLa improves significantly when scaled to 7B parameters. For the first time, we show that a Suno-level, commercial-grade system can be reproduced using academic-scale data and GPU resources. We expect these foundation models to serve as strong baselines for future research and to facilitate practical applications in multimodal content production.

Dongchao Yang, Yuxin Xie, Yuguo Yin +26

Text-to-Music GenerationNeural Audio CodecsControllable Music GenerationAudio UnderstandingAudio-Language ModelsMultimodal Foundation Models
AskPDF
Dec 23, 2025

Aliasing-Free Neural Audio Synthesis

In neural audio synthesis, neural vocoders and codecs are models that reconstruct waveforms from acoustic and latent representations, which are essential to the resulting audio quality. While current models are capable of generating perceptually natural speech, they still struggle with high-fidelity music and singing voice synthesis, as severe aliasing artifacts are introduced by non-linear activation functions and upsampling layers in existing architectures. Although various anti-aliasing techniques have been proposed in digital signal processing, their integration into neural vocoders and codecs remains under-explored. This paper incorporates differentiable anti-aliasing techniques into the activation and upsampling modules to bridge this gap, and thus presents Pupu-Vocoder and Pupu-Codec. We build a test signal benchmark to evaluate the anti-aliased modules, and validate our proposed models on speech, singing voice, music, and audio. Experimental results show that Pupu-Vocoder and Pupu-Codec outperform existing systems on singing voice, music, and audio, while achieving comparable performance on speech. Demos, codes, and checkpoints are available at: VocodexElysium.github.io/AliasingFreeNeuralAudioSynthesis/.

Yicheng Gu, Junan Zhang, Chaoren Wang +3

Spellbrush, Akihabara, Tokyo 101-0021, Japan · Acoustic Laboratory, Department of Information Communications Engineering, Aalto University, Espoo 02150, Finland · School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong 518172, China

Singing Voice SynthesisNeural Audio CodecsNeural VocodersSpeech ProcessingAudio Generation
AskPDF
Nov 26, 2025

Harmonic-Percussive Disentangled Neural Audio Codec for Bandwidth Extension

Bandwidth extension, the task of reconstructing the high-frequency components of an audio signal from its low-passed counterpart, is a long-standing problem in audio processing. In this work, we extend recent advances in neural architectures by framing bandwidth extension as an audio token prediction problem. Specifically, we train a transformer-based language model on the discrete representations produced by a disentangled neural audio codec, where the disentanglement is guided by a Harmonic-Percussive decomposition of the input signals, highlighting spectral structures particularly relevant for bandwidth extension. Our approach introduces a novel codec design that explicitly accounts for the downstream token prediction task, enabling a more effective coupling between codec structure and transformer modeling. This joint design yields high-quality reconstructions of the original signal, as measured by both objective metrics and subjective evaluations. These results highlight the importance of aligning codec disentanglement and representation learning with the generative modeling stage, and demonstrate the potential of global, representation-aware design for advancing bandwidth extension.

Benoît Giniès, Xiaoyu Bie, Olivier Fercoq +1

LTCI, Télécom Paris, Institut Polytechnique de Paris Palaiseau, France

Audio Representation LearningNeural Audio Codecs
AskPDF
Oct 29, 2025

PitchFlower: A flow-based neural audio codec with pitch controllability

We present PitchFlower, a flow-based neural audio codec with explicit pitch controllability. Our approach promotes pitch disentanglement through a simple perturbation: during training, F0 contours are flattened and randomly shifted at the input, while the true F0 is provided as conditioning to regenerate the original audio. A vector-quantization bottleneck prevents pitch recovery, and a flow-based decoder generates high quality audio. Experiments show that PitchFlower achieves accurate pitch control at the level of DSP baselines but at much higher audio quality, and performs on par with state-of-the-art neural approaches. Notably, despite using WORLD-transformed audio for training, our method filters out the vocoder's inherent artifacts, revealing a strong resilience of deep generative modeling to input degradation. This finding suggests that our framework provides a simple and extensible path that could be extended to other speech attributes.

Diego Torres, Axel Roebel, Nicolas Obin

STMS Lab IRCAM - CNRS - Sorbonne Universit´e Paris, France

Neural Audio CodecsControllable Speech GenerationFlow-Based Generative Modeling
AskPDF