EnCodec is an end-to-end trained streaming neural audio codec that uses a single multiscale spectrogram discriminator and a gradient-normalizing loss balancer to achieve higher fidelity than prior methods at the same bitrates for 24 kHz mono and 48 kHz stereo audio.
Speech resynthesis from discrete disentangled self-supervised representations
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
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.
MimicLM achieves better naturalness in zero-shot voice imitation by autoregressively modeling pseudo-parallel data with synthetic sources and real targets, plus interleaved text-audio guidance and preference alignment.
StableToken introduces a multi-branch architecture with bit-wise voting to create noise-robust semantic speech tokens, achieving lower Unit Edit Distance and better SpeechLLM robustness than prior single-path tokenizers.
A self-supervised prosody encoder with speaker disentanglement strategies outperforms raw prosody and HuBERT baselines on pitch reconstruction and prosodic event detection while achieving strong speaker separation.
citing papers explorer
-
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.
-
MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora
MimicLM achieves better naturalness in zero-shot voice imitation by autoregressively modeling pseudo-parallel data with synthetic sources and real targets, plus interleaved text-audio guidance and preference alignment.
-
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
StableToken introduces a multi-branch architecture with bit-wise voting to create noise-robust semantic speech tokens, achieving lower Unit Edit Distance and better SpeechLLM robustness than prior single-path tokenizers.
-
Privacy-preserving Prosody Representation Learning
A self-supervised prosody encoder with speaker disentanglement strategies outperforms raw prosody and HuBERT baselines on pitch reconstruction and prosodic event detection while achieving strong speaker separation.