REVIEW 21 cited by
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
read the original abstract
Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain. While effective, this approach neglects the inductive bias offered by time-frequency representations, resulting in reduntant and computionally-intensive upsampling operations. Fourier-based time-frequency representation is an appealing alternative, aligning more accurately with human auditory perception, and benefitting from well-established fast algorithms for its computation. Nevertheless, direct reconstruction of complex-valued spectrograms has been historically problematic, primarily due to phase recovery issues. This study seeks to close this gap by presenting Vocos, a new model that directly generates Fourier spectral coefficients. Vocos not only matches the state-of-the-art in audio quality, as demonstrated in our evaluations, but it also substantially improves computational efficiency, achieving an order of magnitude increase in speed compared to prevailing time-domain neural vocoding approaches. The source code and model weights have been open-sourced at https://github.com/gemelo-ai/vocos.
Forward citations
Cited by 21 Pith papers
-
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
WavTTS is the first raw-waveform diffusion TTS model using DiT flow matching and multi-scale mel supervision that approaches SOTA latent zero-shot performance while beating prior end-to-end models.
-
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 l...
-
NAC: Neural Action Codec for Vision-Language-Action Models
NAC adapts multi-scale RVQGAN audio codecs with kinematic-specific losses to produce ordered action tokens that yield lower reconstruction error and higher task success than prior tokenizers in VLA models.
-
Staged Depth-Pruning Distillation of a Flow-Matching Text-to-Speech Teacher: A Compact Hindi Speech Synthesizer
Depth-only pruning of a flow-matching Hindi TTS teacher, followed by staged re-fine-tuning, produces 131–190M students with ASR-WER close to the teacher and real-time laptop inference.
-
ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching
A latent flow-matching dialog TTS generates speech in a 4x-compressed 25 Hz space, cutting peak memory about 11x and inference time about 2.2x while keeping UTMOS competitive.
-
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.
-
FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech
FlowTTS-GRPO fine-tunes open-source flow-matching TTS models with multi-objective online RL via ODE-to-SDE conversion, improving speaker similarity and quality on CosyVoice 3.0 and F5-TTS.
-
BareWave: Waveform-Native Flow-Matching Text-to-Speech
BareWave develops a waveform-native flow-matching framework for direct text-to-waveform TTS using representation alignment, staged noise scheduling, and velocity-aware perceptual alignment to achieve strong zero-shot ...
-
UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations
UniPASE extends the low-hallucination PASE framework to universal speech enhancement, restoring seven distortion types at flexible sampling rates with better word-error and speaker-similarity scores than prior generat...
-
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.
-
SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement
SenSE adds language-model semantic guidance to flow-matching generative speech enhancement via a dual-path masked conditioning strategy and reports SOTA results on distorted speech.
-
ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching
ZipL-Dialog cuts peak GPU memory 11.22× and speeds inference 2.23× for multi-minute zero-shot dialog TTS by doing conditional flow matching in a 4× compressed latent space while keeping perceptual naturalness.
-
Unified Audio Intelligence Without Regressing on Text Intelligence
A unified 30B MoE audio-text LLM achieves state-of-the-art audio understanding, generation, and speech tasks while preserving text reasoning comparable to its text-only backbone.
-
FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech
FlowTTS-GRPO applies online RL with weighted multi-objective rewards to flow-matching TTS models via ODE-to-SDE conversion, reporting gains in speaker similarity and perceptual quality on CosyVoice 3.0 and F5-TTS.
-
Synthesizing the Lombard Effect: Multi-Level Control of Speech Clarity and Vocal Effort in TTS
A flow-matching TTS model with pseudo-label training enables continuous disentangled control of vocal effort, articulation, and word-level emphasis to replicate Lombard effect intelligibility gains in noise.
-
PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech Enhancement
PhASE-Flow performs phonetic-conditioned acoustic flow matching entirely in SSL representation space for speech enhancement and reports competitive perceptual quality with only four sampling steps.
-
UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations
UniPASE extends the PASE framework with DeWavLM-Omni to convert degraded speech into high-fidelity, low-hallucination audio across sampling rates via phonetic enhancement, acoustic adaptation, and multi-rate vocoding.
-
Woosh: A Sound Effects Foundation Model
Woosh is a new publicly released foundation model optimized for high-quality sound effect generation from text or video, showing competitive or better results than open alternatives like Stable Audio Open.
-
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.
-
SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations
SARA is a dual-stream VAE that integrates semantic and acoustic streams to achieve high-fidelity reconstruction and natural zero-shot TTS without complex regularizers.
-
Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.