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 like 6.25 Hz.
hub
Hifi-codec: Group-residual vector quantization for high fidelity audio codec
18 Pith papers cite this work, alongside 19 external citations. Polarity classification is still indexing.
18
Pith papers citing it
19
external citations · Pith
abstract
Audio codec models are widely used in audio communication as a crucial technique for compressing audio into discrete representations. Nowadays, audio codec models are increasingly utilized in generation fields as intermediate representations. For instance, AudioLM is an audio generation model that uses the discrete representation of SoundStream as a training target, while VALL-E employs the Encodec model as an intermediate feature to aid TTS tasks. Despite their usefulness, two challenges persist: (1) training these audio codec models can be difficult due to the lack of publicly available training processes and the need for large-scale data and GPUs; (2) achieving good reconstruction performance requires many codebooks, which increases the burden on generation models. In this study, we propose a group-residual vector quantization (GRVQ) technique and use it to develop a novel \textbf{Hi}gh \textbf{Fi}delity Audio Codec model, HiFi-Codec, which only requires 4 codebooks. We train all the models using publicly available TTS data such as LibriTTS, VCTK, AISHELL, and more, with a total duration of over 1000 hours, using 8 GPUs. Our experimental results show that HiFi-Codec outperforms Encodec in terms of reconstruction performance despite requiring only 4 codebooks. To facilitate research in audio codec and generation, we introduce AcademiCodec, the first open-source audio codec toolkit that offers training codes and pre-trained models for Encodec, SoundStream, and HiFi-Codec. Code and pre-trained model can be found on: \href{https://github.com/yangdongchao/AcademiCodec}{https://github.com/yangdongchao/AcademiCodec}
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
AffectCodec applies block-diagonal projections in residual FSQ to explicitly allocate bits to emotion and acoustic subspaces, combined with emotion conditioning, yielding better emotion preservation at low bitrates with competitive acoustic quality.
AffectCodec is an emotion-guided neural speech codec that preserves emotional cues during quantization while maintaining semantic fidelity and prosodic naturalness.
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.
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.
AdaSID adaptively regulates semantic ID overlaps in multimodal recommendations to improve retrieval performance, codebook utilization, and downstream metrics like GMV.
DASB is a new benchmark for discrete audio tokens showing semantic tokens outperform acoustic ones but discrete representations remain less robust than continuous features across domains.
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
PnP reformulates adversarial purification as learning positive-incentive noise to defend speaker verification against attacks with high efficiency and limited impact on genuine utterances.
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.
ECC integrates hyperprior side information, channel-wise context, latent residual prediction, temporal modeling, and entropy skip into a learned entropy model, yielding 39.9% and 76.3% average BD-rate reductions on ViSQOL and PESQ over baselines.
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.
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.
ContextCodec uses a dual-branch encoder with CLIP-style contrastive training on phoneme-aligned context features plus autoregressive refinement to improve quality-intelligibility at bitrates down to 500 bps.
UniAudio-Token enhances semantic speech tokenizers with general audio perception using SAP decomposition and SAE gating, outperforming single-codebook baselines when integrated with LLMs on understanding and generation tasks.
ClariCodec applies GRPO reinforcement learning to a 300 bps neural speech codec, using ASR word-error rate as reward to cut LibriSpeech test-clean WER from 4.64% to 3.55%.
F5-TTS generates natural speech from text via flow matching on DiT with simple text padding, ConvNeXt refinement, and sway sampling, trained on 100K hours multilingual data.
Joint-marginal distillation with adaptive weighting is reported as the best overall alignment loss for speech VAEs across reconstruction, understanding, and generation.
citing papers explorer
-
FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model
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 like 6.25 Hz.
-
AffectCodec: Emotion-Preserving Neural Speech Codec with Block-Diagonal Residual FSQ
AffectCodec applies block-diagonal projections in residual FSQ to explicitly allocate bits to emotion and acoustic subspaces, combined with emotion conditioning, yielding better emotion preservation at low bitrates with competitive acoustic quality.
-
AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
AffectCodec is an emotion-guided neural speech codec that preserves emotional cues during quantization while maintaining semantic fidelity and prosodic naturalness.
-
PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
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.
-
SPG-Codec: Exploring the Role and Boundaries of Semantic Priors in Ultra-Low-Bitrate Neural Speech Coding
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.
-
Beyond Static Collision Handling: Adaptive Semantic ID Learning for Multimodal Recommendation at Industrial Scale
AdaSID adaptively regulates semantic ID overlaps in multimodal recommendations to improve retrieval performance, codebook utilization, and downstream metrics like GMV.
-
DASB - Discrete Audio and Speech Benchmark
DASB is a new benchmark for discrete audio tokens showing semantic tokens outperform acoustic ones but discrete representations remain less robust than continuous features across domains.
-
Unified Audio Intelligence Without Regressing on Text Intelligence
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
-
Positive-Incentive Noise Predictor for Adversarial Purification in Speaker Verification
PnP reformulates adversarial purification as learning positive-incentive noise to defend speaker verification against attacks with high efficiency and limited impact on genuine utterances.
-
Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
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.
-
Benchmarking Neural Speech Compression from a Rate-Distortion Perspective
ECC integrates hyperprior side information, channel-wise context, latent residual prediction, temporal modeling, and entropy skip into a learned entropy model, yielding 39.9% and 76.3% average BD-rate reductions on ViSQOL and PESQ over baselines.
-
Two-Dimensional Quantization for Geometry-Aware Audio Coding
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.
-
SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization
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.
-
ContextCodec: Content-Focused Context Guidance for Ultra-Low Bitrate Speech Coding
ContextCodec uses a dual-branch encoder with CLIP-style contrastive training on phoneme-aligned context features plus autoregressive refinement to improve quality-intelligibility at bitrates down to 500 bps.
-
UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception
UniAudio-Token enhances semantic speech tokenizers with general audio perception using SAP decomposition and SAE gating, outperforming single-codebook baselines when integrated with LLMs on understanding and generation tasks.
-
Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
ClariCodec applies GRPO reinforcement learning to a 300 bps neural speech codec, using ASR word-error rate as reward to cut LibriSpeech test-clean WER from 4.64% to 3.55%.
-
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
F5-TTS generates natural speech from text via flow matching on DiT with simple text padding, ConvNeXt refinement, and sway sampling, trained on 100K hours multilingual data.
-
On the Distillation Loss Functions of Speech VAE for Unified Reconstruction, Understanding, and Generation
Joint-marginal distillation with adaptive weighting is reported as the best overall alignment loss for speech VAEs across reconstruction, understanding, and generation.