Papers for

audio codec developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Neural networks improve audio codec efficiency and quality with low delay

Lightweight Neural Prediction for MDCT-Based Perceptual Audio Coding

Abstract: Perceptual audio codecs often use predictive coding to further reduce signal redundancy. Rather than learning the entire codec pipeline end-to-end, we insert a small neural network as a drop-in, deterministic predictor in an otherwise conventional codec: the network estimates the next Modified Discrete Cosine Transform (MDCT) coefficient block from a short context of reconstructed blocks, and the encoder transmits the quantized residual. We compare Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) predictors against a non-predictive baseline and a per-line Normalized Least Mean Squares (NLMS) linear predictor (similar to the MPEG-2 AAC Main Profile predictor). The CNN consistently outperforms the MLP, the linear predictor, and the baseline in signal-to-noise ratio (SNR), noise-to-mask ratio (NMR), and MUSHRA evaluation scores. Using a 512-sample analysis window (w = 512), our neural predictors recover, and the CNN exceeds, the coded quality obtained by the non-predictive baseline after quadrupling the analysis-window length to w = 2048, at substantially lower algorithmic delay. The CNN uses only 0.13M parameters (roughly 20x fewer than the MLP) and has a decoder real-time factor (RTF) of ~0.10 on a consumer CPU.

Fri 6 NovSound
The gist
Audio codecs compress sounds by predicting parts of the audio so less data needs to be sent. The authors add a small neural network inside a traditional audio codec to better guess the next audio segment, which helps reduce leftover errors and improve sound quality. Their neural network, especially a type called a convolutional neural network, works better than older methods and small networks, achieving higher clarity without slowing down playback. This method keeps processing fast and uses fewer parameters, meaning it can work well on everyday computers.
Open → 2611.10192v1

Perceptual audio coding improves sound quality by smarter bit allocation

Co-Adaptive Entropy Modeling and Rate-Distortion-Optimal Bit Allocation for Perceptual Audio Coding

Abstract: We present a perceptual audio coder in which the entropy-coding model and the bit allocation co-adapt across blocks without model side information. Mantissas are coded by a hybrid of bit packing and arithmetic coding with per-band probability models learned online. Encoder and decoder accumulate identical histograms from decoded blocks and advance the same model state. The model enters bit allocation directly: per-band rate--distortion frontiers combine measured perceptual distortion with entropy-coded rate estimates under the current model, and a dynamic program attains the exact minimum of total objective perceptual distortion for each block's budget under the model's rate estimates, with reservoir carry-over. Under a strict per-block rate, entropy-coding-aware bit allocation lowers this distortion (band noise-to-mask ratio in linear scale) by 15-24% relative to the same solver without it, and co-adaptation removes a further 3-4% (up to 15% on oboe) that a backward-adaptive coder alone cannot realize in one pass; a MUSHRA test at 80 kbps per channel confirms the ranking.

Mon 12 OctInformation Theory
The gist
Compressing audio often means choosing which parts to keep and which to simplify so it still sounds good. This paper presents a method where the models used to compress sound and the way bits are shared adapt together for each chunk of audio without extra info. The authors show that this approach reduces distortion and improves perceived sound quality compared to previous methods. They tested it with listening tests and found meaningful improvements at common streaming quality levels.
Open → 2610.17459v1

Neural audio coder reconstructs high quality sound at low bitrates

HE-NAC: High-Efficiency Neural Audio Coding via Hierarchical and Residual Multi-Band Quantization

Abstract: High-fidelity audio coding requires faithful reconstruction of perceptually important high-frequency components, which are often lost due to the aggressive temporal decimation and quantization of neural codecs. State-of-the-art neural audio coding methods rely on adversarial learning to hallucinate these missing components, yielding perceptually plausible but imprecise reconstructions; a limitation for high-fidelity music applications. As a remedy, we propose high-efficiency neural audio coding (HE-NAC), which provides a multi-band extension of the popular residual vector quantization (RVQ) scheme. HE-NAC introduces an effective training mechanism that harmonizes a bitrate-free blind upsampling process, residual learning to compensate it with minimal bitrate, and a multi-head decoder architecture for band-specific reconstruction. As a result, HE-NAC achieves a balanced trade-off, reliably reconstructing the core-band ($\leq$ 3 kHz) component while preserving overall sound fidelity. Subjective listening tests and objective evaluations demonstrate that HE-NAC outperforms both the DAC baseline and MPEG HE-AAC at equal or lower bitrates.

Sun 11 OctSound
The gist
Encoding audio into small digital files often loses important high-frequency sounds, making music less clear. The authors developed a new neural audio coder that splits sounds into different frequency bands and fixes missing details with smart learning techniques. This method keeps important low-frequency sounds while better preserving the overall quality of the music. Tests show it works better than some common audio compression standards at similar or lower file sizes.
Open → 2610.15243v1

Ensemble method adds confidence intervals to audio quality scores

Ensemble-Based Perceptual Audio Quality Assessment with Confidence Intervals

Abstract: Objective audio quality metrics typically provide point estimates, whereas listening tests yield score distributions from which mean opinion scores (MOS), confidence intervals (CIs), and significance decisions are derived. We propose a lightweight intrusive metric that combines a PEAQ-style perceptual front-end (ITU-R BS.1387) with a bagging ensemble of regressors. Calibration with subjective data aligns ensemble outputs with listener scores. The resulting item-dependent score distributions enable uncertainty assessment, panel-size-matched CIs, and identification of less conclusive predictions. Calibration improves agreement with subjective distributions and CI coverage across all evaluated datasets while preserving MOS accuracy. Using only 11 fixed PEAQ features, low-capacity regressors, and public training data, the method performs comparably to more data-intensive end-to-end approaches. Its output can support uncertainty-aware assessment and target listening tests towards uncertain conditions. The distributions also enable approximate pairwise comparisons, but not yet reliable significance inference.

Mon 5 OctSound
The gist
Measuring how good audio sounds is tricky because people’s opinions vary, and traditional methods only give single scores without showing uncertainty. The authors created a lightweight system that uses multiple simple models together to predict audio quality and also estimate how confident those predictions are. This helps identify when the results are less certain and could guide further listening tests more efficiently. Their approach uses few features and public data but matches more complex methods in accuracy.
Open → 2610.06569v1

Methods to measure compression limits of quantized Gaussian signals

Computing the entropy rate of a quantized stationary Gaussian process

Abstract: We consider a stationary Gaussian process observed after uniform quantization. The entropy rate of the resulting integer sequence is the fundamental limit on lossless compression of the quantized signal, but it has no closed form, and the classical high-resolution approximation breaks down whenever the spectral density is small or vanishing on part of the band, as happens routinely after smoothing or filtering. Here we present two methods for computing the rate. The first is an analytical approximation obtained by combining an exact dithering identity with the Kolmogorov-Szegő formula; the quantization noise power acts as a floor on the spectral density, so the rate remains finite where the classical formula fails. The second is a Monte Carlo estimate of the exact rate. Its minimum-phase spectral factor represents the process as a finite moving average of Gaussian innovations, making the quantized sequence a hidden Markov process whose optimal (fully adapted) particle filter is available in closed form; by the Shannon-McMillan-Breiman theorem the rate follows from the filter's log-likelihood on a single long sequence. In experiments across six process families, the approximation agrees with the estimate to within a few millibits per sample over most of the parameter range for quantization steps up to the signal standard deviation, including strongly filtered processes on which the classical formula fails; at the most strongly filtered points the discrepancy grows to a few percent of the rate, and for much coarser steps the estimator should be used. We also compare lossless coders against this limit. At a step of one quarter of the standard deviation, linear predictive coding followed by an entropy coder comes within 2 to 4 percent of the entropy rate and FLAC within 3 to 32 percent, whereas five general-purpose compressors on the raw samples remain 12 to 89 percent above it.

Wed 16 SeptInformation Theory
The gist
When a smooth, repeating signal is turned into numbers by rounding, it becomes harder to perfectly compress without losing any information. The authors studied how to calculate the minimum possible size for such compressed data when the original signal is a Gaussian type with certain spectral properties. They developed a new formula that works well even when older approaches fail, and a computer simulation method that estimates the same limit accurately. Their work helps understand how close actual compression methods come to the theoretical best.
Open → 2609.18784v1

New method improves sequential data compression balancing error and perception

Sequential Lossy Compression With Causal Conditional Perception

Abstract: In this paper, we study sequential lossy compression under a causal conditional perception criterion comparing source and reconstruction distributions given the same reconstruction history. For first-order Markov sources, we formulate the finite-horizon nonanticipative rate-distortion-perception function (NRDPF) with stagewise constraints and establish one-shot lower and upper bounds on the minimum variable-length sum rate using a strengthened strong functional-representation lemma (SFRL) and common randomness. For time-varying scalar Gauss--Markov sources under pointwise mean-squared error (MSE) and conditional squared Wasserstein-$2$ fidelity, we prove Gaussian optimality, derive a log-variance characterization, and obtain a closed-form solution that recovers the classical Gaussian nonanticipative rate-distortion function (NRDF) when perception is unconstrained and the classical Gaussian RDPF when the source is stationary and memoryless.

Tue 8 SeptInformation Theory
The gist
This paper looks at how to compress sequences of data (like audio or video) while keeping the compressed version looking or sounding close to the original in a meaningful way. The authors focus on compressing data step-by-step without looking ahead, ensuring the reconstructed data matches the perception of the original when considering the past data. They develop mathematical tools and formulas to find the best compression rate when trying to balance accuracy and how the output is perceived. Their approach applies to certain statistical models of data and includes exact solutions for Gaussian cases, extending known results in data compression.
Open → 2609.08611v1