Neural audio autoencoders have become a core component of compression, feature extraction, and generation. However, while existing systems support variable bitrate, the vast majority of models still operate at a fixed latent frame-rate, allocating equal temporal budget to regions with very different information density, which can result in unnecessarily long sequences. We introduce Elastic Time, a dynamic frame-rate bottleneck that converts fixed-frame-rate autoencoders to dynamic ones. Our method learns a lightweight latent predictor used to decide which frames can be skipped and later reconstructed, enabling efficient greedy boundary selection at inference. Experiments show our method enables deployment-time rate control while improving efficiency-quality tradeoffs relative to baselines. Overall, we provide a flexible mechanism for adjusting temporal resolution in audio autoencoders, potentially facilitating more efficient downstream modeling for generation and long-context tasks.
Indiana University（印第安纳大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals. For neural audio codecs, however, the objective nature of the loss function usually leads to suboptimal sound quality as well as high run-time complexity due to the large model size. In this work, we present a psychoacoustic calibration scheme to re-define the loss functions of neural audio coding systems so that it can decode signals more perceptually similar to the reference, yet with a much lower m…
Dolby Laboratories, Inc.（杜比实验室公司）；Dolby Sweden AB（杜比瑞典公司）
We propose a neural audio generative model, MDCTNet, operating in the perceptually weighted domain of an adaptive modified discrete cosine transform (MDCT). The architecture of the model captures correlations in both time and frequency directions with recurrent layers (RNNs). An audio coding system is obtained by training MDCTNet on a diverse set of fullband monophonic audio signals at 48 kHz sampling, conditioned by a perceptual audio encoder. In a subjective listening test with ten excerpts chosen to be balanced across content types, yet stressful for both codecs, the mean performance of the…
Indiana University（印第安纳大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
Spectral sub-bands do not portray the same perceptual relevance. In audio coding, it is therefore desirable to have independent control over each of the constituent bands so that bitrate assignment and signal reconstruction can be achieved efficiently. In this work, we present a novel neural audio coding network that natively supports a multi-band coding paradigm. Our model extends the idea of compressed skip connections in the U-Net-based codec, allowing for independent control over both core and high band-specific reconstructions and bit allocation. Our system reconstructs the full-band sign…
When detecting anomalies in audio, it can often be necessary to consider concept drift: the distribution of the data may drift over time because of dynamically changing environments, and anomalies may become normal as time elapses. We propose to use adaptive Huffman coding for anomaly detection in audio with concept drift. Compared with the existing method of adaptive Gaussian mixture modeling (AGMM), adaptive Huffman coding does not require a priori information about the clusters and can adjust the number of clusters dynamically depending on the amount of variation in the audio. To control th…
Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs. This is mostly achieved by following the VQ-VAE paradigm where blind features are learned, vector-quantized and coded. In this paper, instead of blind end-to-end learning, we propose to learn disentangled features for real-time neural speech coding. Specifically, more global-like speaker identity and local content features are learned with disentanglement to represent speech. Such a compact feature decomposition not only achieves better coding efficiency by…
Sony Computer Science Laboratory（索尼计算机科学实验室）；LTCI, Télécom Paris, Institut Polytechnique de Paris（LTCI，巴黎电信学院，巴黎综合理工学院）
Influenced by the field of Computer Vision, Generative Adversarial Networks (GANs) are often adopted for the audio domain using fixed-size two-dimensional spectrogram representations as the "image data". However, in the (musical) audio domain, it is often desired to generate output of variable duration. This paper presents VQCPC-GAN, an adversarial framework for synthesizing variable-length audio by exploiting Vector-Quantized Contrastive Predictive Coding (VQCPC). A sequence of VQCPC tokens extracted from real audio data serves as conditional input to a GAN architecture, providing step-wise t…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；Hong Kong University of Science and Technology（香港科技大学）；University of Science and Technology of China（中国科学技术大学）
Large-scale deep neural networks (DNNs) such as convolutional neural networks (CNNs) have achieved impressive performance in audio classification for their powerful capacity and strong generalization ability. However, when training a DNN model on low-resource tasks, it is usually prone to overfitting the small data and learning too much redundant information. To address this issue, we propose to use variational information bottleneck (VIB) to mitigate overfitting and suppress irrelevant information. In this work, we conduct experiments ona 4-layer CNN. However, the VIB framework is ready-to-us…
University of Erlangen-Nuremberg（埃尔朗根-纽伦堡大学）；International Audio Laboratories（国际音频实验室）
Previous DCASE challenges contributed to an increase in the performance of acoustic scene classification systems. State-of-the-art classifiers demand significant processing capabilities and memory which is challenging for resource-constrained mobile or IoT edge devices. Thus, it is more likely to deploy these models on more powerful hardware and classify audio recordings previously uploaded (or streamed) from low-power edge devices. In such scenario, the edge device may apply perceptual audio coding to reduce the transmission data rate. This paper explores the effect of perceptual audio coding…
APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm
National Engineering Research Center of Speech and Language Information Processing（国家语言语音信息处理工程研究中心）；University of Science and Technology of China（中国科学技术大学）
Communication University of China（中国传媒大学）；Microsoft Research Asia（微软亚洲研究院）
Bitrate scalability is a desirable feature for audio coding in real-time communications. Existing neural audio codecs usually enforce a specific bitrate during training, so different models need to be trained for each target bitrate, which increases the memory footprint at the sender and the receiver side and transcoding is often needed to support multiple receivers. In this paper, we introduce a cross-scale scalable vector quantization scheme (CSVQ), in which multi-scale features are encoded progressively with stepwise feature fusion and refinement. In this way, a coarse-level signal is recon…
Communication University of China（中国传媒大学）；Microsoft Research Asia（微软亚洲研究院）
Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low latency for RTC. It takes an encoder-temporal filtering-decoder paradigm that has seldom been investigated in audio coding. An interleaved structure is proposed for temporal filtering to capture both short-term and long-term temporal dependencies. Furthermore, with end-to-end optimization, the TFNet is jointly optimized with speech enhancement and packet loss…
University of California Santa Barbara（加州大学圣巴巴拉分校）
Advances in virtual reality have generated substantial interest in accurately reproducing and storing spatial audio in the higher order ambisonics (HOA) representation, given its rendering flexibility. Recent standardization for HOA compression adopted a framework wherein HOA data are decomposed into principal components that are then encoded by standard audio coding, i.e., frequency domain quantization and entropy coding to exploit psychoacoustic redundancy. A noted shortcoming of this approach is the occasional mismatch in principal components across blocks, and the resulting suboptimal tran…
Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding
Xi’an Jiaotong University（西安交通大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院）
Indiana University（印第安纳大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
An autoencoder-based codec employs quantization to turn its bottleneck layer activation into bitstrings, a process that hinders information flow between the encoder and decoder parts. To circumvent this issue, we employ additional skip connections between the corresponding pair of encoder-decoder layers. The assumption is that, in a mirrored autoencoder topology, a decoder layer reconstructs the intermediate feature representation of its corresponding encoder layer. Hence, any additional information directly propagated from the corresponding encoder layer helps the reconstruction. We implement…
End-to-end audio-visual learning for cochlear implant sound coding simulations in noisy environments
Graduate Institute of Electronics Engineering（电子工程研究所）；the Department of Electrical Engineering, National Taiwan University, Taipei 106319, Taiwan（国立台湾大学电子工程系）；Research Center for Information Technology Innovation Technology, Academia Sinica, Taipei 115201, Taiwan（中科院资讯科技创新研究中心）；Department of Electrical Engineering, Chung Yuan Christian University, Taoyuan 320314, Taiwan（Chung Yuan Christian University 电子工程系）
We present a preliminary study on an end-to-end variational autoencoder (VAE) for sound morphing. Two VAE variants are compared: VAE with dilation layers (DC-VAE) and VAE only with regular convolutional layers (CC-VAE). We combine the following loss functions: 1) the time-domain mean-squared error for reconstructing the input signal, 2) the Kullback-Leibler divergence to the standard normal distribution in the bottleneck layer, and 3) the classification loss calculated from the bottleneck representation. On a database of spoken digits, we use 1-nearest neighbor classification to show that the …
Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
IIE, Chinese Academy of Sciences（中国科学院信息工程研究所）；Zhejiang University（浙江大学）；ByteDance China（字节跳动中国）；VCIP & TMCC & DISSec, College of Computer Science, Nankai University（VCIP与TMCC与DISSec，南开大学计算机学院）；School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；Department of Psychological and Cognitive Sciences, Tsinghua University（清华大学心理学与认知科学系）；University of Chinese Academy of Sciences（中国科学院大学）
We propose a method for learning de-identified prosody representations from raw audio using a contrastive self-supervised signal. Whereas prior work has relied on conditioning models on bottlenecks, we introduce a set of inductive biases that exploit the natural structure of prosody to minimize timbral information and decouple prosody from speaker representations. Despite aggressive downsampling of the input and having no access to linguistic information, our model performs comparably to state-of-the-art speech representations on DAMMP, a new benchmark we introduce for spoken language understa…
SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models
Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin, EIT（宁波空间智能与数字衍生关键实验室，数字孪生研究院，EIT）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）；Shenzhen University of Advanced Technology（深圳先进技术大学）；Shenzhen MSU-BIT University（深圳MSU-BIT大学）；Amazon AGI（亚马逊人工智能）
Acoustics Research Institute, Austrian Academy of Sciences（奥地利科学院声学研究所）；Swiss Data Science Center, ETH Zürich（苏黎世联邦理工学院瑞士数据科学中心）
We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The proposed DNN structure was trained on audio signals containing music and musical instruments, separately, with 64-ms long gaps. The input to the DNN was the context, i.e., the signal surrounding the gap, transformed into time-frequency (TF) coefficients. Our results were compared to those obtained from a reference method based on linear predictive coding (LPC). For music, our …
With active research in audio compression techniques yielding substantial breakthroughs, spectral reconstruction of low-quality audio waves remains a less indulged topic. In this paper, we propose a novel approach for reconstructing higher frequencies from considerably longer sequences of low-quality MP3 audio waves. Our technique involves inpainting audio spectrograms with residually stacked autoencoder blocks by manipulating individual amplitude and phase values in relation to perceptual differences. Our architecture presents several bottlenecks while preserving the spectral structure of the…
Graph-based Transform is one of the recent transform coding methods which has been used successfully in the state-of-art data decorrelation applications. In this paper, we propose a Graph-based Transform (GT) for audio compression. Hence, we introduce a proper graph structure for audio. Then the audio frames are projected onto an orthogonal matrix consisting of eigenvectors of the introduced graph matrix, leading to the sparse coefficients. The results show that the proposed method outperforms the conventional transform methods like Discrete Cosine Transform (DCT) and Walsh-Hadamard Transform …
Microsoft Research Asia（微软亚洲研究院）；Communication University of China（中国传媒大学）
Neural audio coding has shown very promising results recently in the literature to largely outperform traditional codecs but limited attention has been paid on its error resilience. Neural codecs trained considering only source coding tend to be extremely sensitive to channel noises, especially in wireless channels with high error rate. In this paper, we investigate how to elevate the error resilience of neural audio codecs for packet losses that often occur during real-time communications. We propose a feature-domain packet loss concealment algorithm (FD-PLC) for real-time neural speech codin…
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）
Audio processing methods operating on a time-frequency representation of the signal can introduce unpleasant sounding artifacts known as musical noise. These artifacts are observed in the context of audio coding, speech enhancement, and source separation. The change in kurtosis of the power spectrum introduced during the processing was shown to correlate with the human perception of musical noise in the context of speech enhancement, leading to the proposal of measures based on it. These baseline measures are here shown to correlate with human perception only in a limited manner. As ground tru…
I present a method for lossy transform coding of digital audio that uses the Weyl symbol calculus for constructing the encoding and decoding transformation. The method establishes a direct connection between a time-frequency representation of the signal dependent threshold of masked noise and the encode/decode pair. The formalism also offers a time-frequency measure of perceptual entropy.
