Search

This paper introduces FlowMAC, a novel neural audio codec for high-quality general audio compression at low bit rates based on conditional flow matching (CFM). FlowMAC jointly learns a mel spectrogram encoder, quantizer and decoder. At inference time the decoder integrates a continuous normalizing flow via an ODE solver to generate a high-quality mel spectrogram. This is the first time that a CFM-based approach is applied to general audio coding, enabling a scalable, simple and memory efficient training. Our subjective evaluations show that FlowMAC at 3 kbps achieves similar quality as state-of-the-art GAN-based and DDPM-based neural audio codecs at double the bit rate. Moreover, FlowMAC offers a tunable inference pipeline, which permits to trade off complexity and quality. This enables real-time coding on CPU, while maintaining high perceptual quality., Comment: Submitted to ICASSP 2025

Audio and speech coding lack unified evaluation and open-source testing. Many candidate systems were evaluated on proprietary, non-reproducible, or small data, and machine learning-based codecs are often tested on datasets with similar distributions as trained on, which is unfairly compared to digital signal processing-based codecs that usually work well with unseen data. This paper presents a full-band audio and speech coding quality benchmark with more variable content types, including traditional open test vectors. An example use case of audio coding quality assessment is presented with open-source Opus, 3GPP's EVS, and recent ETSI's LC3 with LC3+ used in Bluetooth LE Audio profiles. Besides, quality variations of emotional speech encoding at 16 kbps are shown. The proposed open-source benchmark contributes to audio and speech coding democratization and is available at https://github.com/JozefColdenhoff/OpenACE.

This paper explores the integration of model-based and data-driven approaches within the realm of neural speech and audio coding systems. It highlights the challenges posed by the subjective evaluation processes of speech and audio codecs and discusses the limitations of purely data-driven approaches, which often require inefficiently large architectures to match the performance of model-based methods. The study presents hybrid systems as a viable solution, offering significant improvements to the performance of conventional codecs through meticulously chosen design enhancements. Specifically, it introduces a neural network-based signal enhancer designed to post-process existing codecs' output, along with the autoencoder-based end-to-end models and LPCNet--hybrid systems that combine linear predictive coding (LPC) with neural networks. Furthermore, the paper delves into predictive models operating within custom feature spaces (TF-Codec) or predefined transform domains (MDCTNet) and examines the use of psychoacoustically calibrated loss functions to train end-to-end neural audio codecs. Through these investigations, the paper demonstrates the potential of hybrid systems to advance the field of speech and audio coding by bridging the gap between traditional model-based approaches and modern data-driven techniques., Comment: Published in IEEE Signal Processing Magazine

This paper introduces a novel adaptation approach for first-order pre- and de-emphasis filters, an essential tool in many speech and audio codecs to increase coding efficiency and perceived quality. The proposed zero-bit self-adaptation approach differs from classical forward and backward adaptation approaches in that the de-emphasis coefficient is estimated at the receiver, from the decoded pre-emphasized signal. This eliminates the need to transmit information that arises from forward adaptation as well as the signal-filter lag that is inherent in backward adaptation. Evaluation results show that the de-emphasis coefficient can be estimated accurately from the decoded pre-emphasized signal and that the proposed zero-bit self-adaptation approach provides comparable subjective improvement to forward adaptation., Comment: This paper has been accepted by the 47th International Conference on Telecommunications and Signal Processing (TSP 2024)

In this paper, we proposed AI-based audio coding using MFCC features in an adversarial setting. We combined a conventional encoder with an adversarial learning decoder to better reconstruct the original waveform. Since GAN gives implicit density estimation, therefore, such models are less prone to overfitting. We compared our work with five well-known codecs namely AAC, AC3, Opus, Vorbis, and Speex, performing on bitrates from 2kbps to 128kbps. MFCCGAN_36k achieved the state-of-the-art result in terms of SNR despite a lower bitrate in comparison to AC3_128k, AAC_112k, Vorbis_48k, Opus_48k, and Speex_48K. On the other hand, MFCCGAN_13k also achieved high SNR=27 which is equal to that of AC3_128k, and AAC_112k while having a significantly lower bitrate (13 kbps). MFCCGAN_36k achieved higher NISQA-MOS results compared to AAC_48k while having a 20% lower bitrate. Furthermore, MFCCGAN_13k obtained NISQAMOS= 3.9 which is much higher than AAC_24k, AAC_32k, AC3_32k, and AAC_48k. For future work, we finally suggest adopting loss functions optimizing intelligibility and perceptual metrics in the MFCCGAN structure to improve quality and intelligibility simultaneously., Comment: Accepted in ABU Technical Review journal 2023/3

Audio coding is an essential module in the real-time communication system. Neural audio codecs can compress audio samples with a low bitrate due to the strong modeling and generative capabilities of deep neural networks. To address the poor high-frequency expression and high computational cost and storage consumption, we proposed an integrated framework that utilizes a neural network to model wide-band components and adopts traditional signal processing to compress high-band components according to psychological hearing knowledge. Inspired by auditory perception theory, a perception-based loss function is designed to improve harmonic modeling. Besides, generative adversarial network (GAN) compression is proposed for the first time for neural audio codecs. Our method is superior to prior advanced neural codecs across subjective and objective metrics and allows real-time inference on desktop and mobile.

In recent years, audio coding technology has been standardized based on several frameworks that incorporate linear predictive coding (LPC). However, coding the transient signal using frequency-domain LP residual signals remains a challenge. To address this, temporal noise shaping (TNS) can be adapted, although it cannot be effectively operated since the estimated temporal envelope in the modified discrete cosine transform (MDCT) domain is accompanied by the time-domain aliasing (TDA) terms. In this study, we propose the modulated complex lapped transform-based coding framework integrated with transform coded excitation (TCX) and complex LPC-based TNS (CTNS). Our approach uses a 50\% overlap window and switching scheme for the CTNS to improve the coding efficiency. Additionally, an adaptive calculation of the target bits for the sub-bands using the frequency envelope information based on the quantized LPC coefficients is proposed. To minimize the quantization mismatch between both modes, an integrated quantization for real and complex values and a TDA augmentation method that compensates for the artificially generated TDA components during switching operations are proposed. The proposed coding framework shows a superior performance in both objective metrics and subjective listening tests, thereby demonstrating its low bit-rate audio coding., Comment: accepted to WASPAA (IEEE Workshop on Applications of Signal Processing to Audio and Acoustics) 2023

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 signal mainly from the condensed core-band code, therefore exploiting and showcasing its bandwidth extension capabilities to its fullest. Meanwhile, the low-bitrate high-band code helps the high-band reconstruction similarly to MPEG audio codecs' spectral bandwidth replication. MUSHRA tests show that the proposed model not only improves the quality of the core band by explicitly assigning more bits to it but retains a good quality in the high-band as well., Comment: Accepted to ICASSP 2023. For resources and examples, see https://saige.sice.indiana.edu/research-projects/HARP-Net/

Over the past decade, audio coding technology has seen standardization and the development of many frameworks incorporated with linear predictive coding (LPC). As LPC reduces information in the frequency domain, LP-based frequency-domain noise-shaping (FDNS) was previously proposed. To code transient signals effectively, FDNS with temporal noise shaping (TNS) has emerged. However, these mainly operated in the modified discrete cosine transform domain, which essentially accompanies time domain aliasing. In this paper, a unified noise-shaping (UNS) framework including FDNS and complex LPC-based TNS (CTNS) in the DFT domain is proposed to overcome the aliasing issues. Additionally, a modified polar quantizer with phase contrast control is proposed, which saves phase bits depending on the frequency envelope information. The core coding feasibility at low bit rates is verified through various objective metrics and subjective listening evaluations., Comment: Submitted and accepted in ICASSP (International Conference on Acoustics, Speech, and Signal Processing) 2023

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 proposed system for 24 kb/s variable bitrate (VBR) is similar to that of Opus at twice the bitrate., Comment: Five pages, five figures

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 model complexity. The proposed loss function incorporates the global masking threshold, allowing the reconstruction error that corresponds to inaudible artifacts. Experimental results show that the proposed model outperforms the baseline neural codec twice as large and consuming 23.4% more bits per second. With the proposed method, a lightweight neural codec, with only 0.9 million parameters, performs near-transparent audio coding comparable with the commercial MPEG-1 Audio Layer III codec at 112 kbps.

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 this kind of skip connections in the form of additional autoencoders, each of which is a small codec that compresses the massive data transfer between the paired encoder-decoder layers. We empirically verify that the proposed hyper-autoencoded architecture improves perceptual audio quality compared to an ordinary autoencoder baseline., Comment: Accepted to the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021, Mohonk Mountain House, New Paltz, NY

Enhancement algorithms for wireless acoustics sensor networks~(WASNs) are indispensable with the increasing availability and usage of connected devices with microphones. Conventional spatial filtering approaches for enhancement in WASNs approximate quantization noise with an additive Gaussian distribution, which limits performance due to the non-linear nature of quantization noise at lower bitrates. In this work, we propose a postfilter for enhancement based on Bayesian statistics to obtain a multidevice signal estimate, which explicitly models the quantization noise. Our experiments using PSNR, PESQ and MUSHRA scores demonstrate that the proposed postfilter can be used to enhance signal quality in ad-hoc sensor networks.

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 transitions in the data fed to the audio coder. Instead, we propose a framework where singular value decomposition (SVD) is performed after transformation to the frequency domain via the modified discrete cosine transform (MDCT). This framework not only ensures smooth transition across blocks, but also enables frequency dependent SVD for better energy compaction. Moreover, we introduce a novel noise substitution technique to compensate for suppressed ambient energy in discarded higher order ambisonics channels, which significantly enhances the perceptual quality of the reconstructed HOA signal. Objective and subjective evaluation results provide evidence for the effectiveness of the proposed framework in terms of both higher compression gains and better perceptual quality, compared to existing methods., Comment: 5 pages, 3 figures