REVIEW 7 cited by
SoundStream: An End-to-End Neural Audio Codec
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
read the original abstract
We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully convolutional encoder/decoder network and a residual vector quantizer, which are trained jointly end-to-end. Training leverages recent advances in text-to-speech and speech enhancement, which combine adversarial and reconstruction losses to allow the generation of high-quality audio content from quantized embeddings. By training with structured dropout applied to quantizer layers, a single model can operate across variable bitrates from 3kbps to 18kbps, with a negligible quality loss when compared with models trained at fixed bitrates. In addition, the model is amenable to a low latency implementation, which supports streamable inference and runs in real time on a smartphone CPU. In subjective evaluations using audio at 24kHz sampling rate, SoundStream at 3kbps outperforms Opus at 12kbps and approaches EVS at 9.6kbps. Moreover, we are able to perform joint compression and enhancement either at the encoder or at the decoder side with no additional latency, which we demonstrate through background noise suppression for speech.
Forward citations
Cited by 7 Pith papers
-
ITGPT: A Transformer Based Architecture for the Generation of Dance Dance Revolution and In the Groove Charts
ITGPT, a transformer pipeline, generates DDR/ITG arrow charts from audio with better accuracy and roughly 7x lower generation time than the prior ConvLSTM approach.
-
AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation
A four-part benchmark plus a semantic/acoustic token taxonomy for comparing audio codecs, with correlation analysis across ten models.
-
UniSGR: Unified Framework for Semantic ID Generation and Ranking
A two-stage generative recommender jointly optimizes value-aware multi-token prediction and multi-objective ranking on shared semantic IDs, with STARK speeding beam search.
-
EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization
A lightweight autoencoder with residual vector quantization and adversarial training compresses wind turbine pressure data by up to 10,240x with under 3% error, running on a low-power GAP9 MCU.
-
Analysis of Speaker Verification Performance Trade-offs with Neural Audio Codec Transmission
Neural audio codecs match or beat Opus for speaker verification on VoxCeleb1 below 12 kbps and stay within about 1.5 percentage points EER above it.
-
Distilling Spectrograms into Tokens: Fast and Lightweight Bioacoustic Classification for BirdCLEF+ 2025
The authors report that a Word2Vec-style model on K-means spectrogram tokens classifies BirdCLEF+ 2025 soundscapes in about 6 minutes, reaching a public ROC-AUC of 0.559, far below transfer-learning baselines.
-
WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration
WaveLLDM, a lightweight latent diffusion model with a neural codec, achieves low spectral distortion (LSD 0.48-0.60) on speech restoration but scores far below SOTA on PESQ and STOI.
Discussion (0). Continue with ORCID to comment.