Speech signals in real-world environments are frequently affected by various distortions such as additive noise, reverberation, and bandwidth limitation, which may appear individually or in combination. Traditional speech enhancement methods typically rely on either masking, which focuses on suppressing non-speech components while preserving observable structure, or mapping, which seeks to recover clean speech through direct transformation of the input. Each approach offers strengths in specific scenarios but may be less effective outside its target conditions. We propose the Erase and Draw Network (EDNet), a distortion-agnostic speech enhancement framework designed to handle a broad range of distortion types without prior assumptions about task or input characteristics. EDNet consists of two main components: (1) the Gating Mamba (GM) module, which adaptively combines masking and mapping through a learnable gating mechanism that selects between suppression (Erase) and reconstruction (Draw) based on local signal features, and (2) Phase Shift-Invariant Training (PSIT), a shift tolerant supervision strategy that improves phase estimation by enabling dynamic alignment during training while remaining compatible with standard loss functions. Experimental results on denoising, dereverberation, bandwidth extension, and multi distortion enhancement tasks show that EDNet consistently achieves strong performance across conditions, demonstrating its architectural flexibility and adaptability to diverse task settings.
This study evaluates the Extreme Bandwidth Extension Network (EBEN) model on body-conduction sensors through listening tests. Using the Vibravox dataset, we assess intelligibility with a French Modified Rhyme Test, speech quality with a MUSHRA (MUltiple Stimuli with Hidden Reference and Anchor) protocol and speaker identity preservation with an A/B identification task. The experiments involved male and female speakers recorded with a forehead accelerometer, rigid in-ear and throat microphones. The results confirm that EBEN enhances both speech quality and intelligibility. It slightly degrades speaker identification performance when applied to female speakers' throat microphone recordings. The findings also demonstrate a correlation between Short-Time Objective Intelligibility (STOI) and perceived quality in body-conducted speech, while speaker verification using ECAPA2-TDNN aligns well with identification performance. No tested metric reliably predicts EBEN's effect on intelligibility.
Audio bandwidth extension is the task of reconstructing missing high frequency components of bandwidth-limited audio signals, where bandwidth limitation is a common issue for audio signals due to several reasons, including channel capacity and data constraints. While conventional spectral band replication is a well-established parametric approach to audio bandwidth extension, the SBR usually entails coarse feature extraction and reconstruction techniques, which leads to limitations when processing various types of audio signals. In parallel, numerous deep neural network-based audio bandwidth extension methods have been proposed. These DNN-based methods are usually referred to as blind BWE, as these methods do not rely on prior information extracted from original signals, and only utilize given low frequency band signals to estimate missing high frequency components. In order to replace conventional SBR with DNNs, simply adopting existing DNN-based methodologies results in suboptimal performance due to the blindness of these methods. My proposed research suggests a new approach to parametric non-blind bandwidth extension, as DNN-based side information extraction and DNN-based bandwidth extension are performed only at the front and end of the audio coding pipeline.
Neural audio autoencoders create compact latent representations that preserve perceptually important information, serving as the foundation for both modern audio compression systems and generation approaches like next-token prediction and latent diffusion. Despite their prevalence, most audio processing operations, such as spatial and spectral up-sampling, still inefficiently operate on raw waveforms or spectral representations rather than directly on these compressed representations. We propose a framework that performs audio processing operations entirely within an autoencoder's latent space, eliminating the need to decode to raw audio formats. Our approach dramatically simplifies training by operating solely in the latent domain, with a latent L1 reconstruction term, augmented by a single latent adversarial discriminator. This contrasts sharply with raw-audio methods that typically require complex combinations of multi-scale losses and discriminators. Through experiments in bandwidth extension and mono-to-stereo up-mixing, we demonstrate computational efficiency gains of up to 100x while maintaining quality comparable to post-processing on raw audio. This work establishes a more efficient paradigm for audio processing pipelines that already incorporate autoencoders, enabling significantly faster and more resource-efficient workflows across various audio tasks.
In practical application of speech codecs, a multitude of factors such as the quality of the radio connection, limiting hardware or required user experience necessitate trade-offs between achievable perceptual quality, engendered bitrate and computational complexity. Most conventional and neural speech codecs operate on wideband (WB) speech signals to achieve this compromise. To further enhance the perceptual quality of coded speech, bandwidth extension (BWE) of the transmitted speech is an attractive and popular technique in conventional speech coding. In contrast, neural speech codecs are typically trained end-to-end to a specific set of requirements and are often not easily adaptable. In particular, they are typically trained to operate at a single fixed sampling rate. With the Universal Bandwidth Extension Generative Adversarial Network (UBGAN), we propose a modular and lightweight GAN-based solution that increases the operational flexibility of a wide range of conventional and neural codecs. Our model operates in the subband domain and extends the bandwidth of WB signals from 8 kHz to 16 kHz, resulting in super-wideband (SWB) signals. We further introduce two variants, guided-UBGAN and blind-UBGAN, where the guided version transmits quantized learned representation as a side information at a very low bitrate additional to the bitrate of the codec, while blind-BWE operates without such side-information. Our subjective assessments demonstrate the advantage of UBGAN applied to WB codecs and highlight the generalization capacity of our proposed method across multiple codecs and bitrates.
Audio in the real world may be perturbed due to numerous factors, causing the audio quality to be degraded. The following work presents an audio restoration model tailored for high-res music at 44.1kHz. Our model, Audio-to-Audio Schrodinger Bridges (A2SB), is capable of both bandwidth extension (predicting high-frequency components) and inpainting (re-generating missing segments). Critically, A2SB is end-to-end without need of a vocoder to predict waveform outputs, able to restore hour-long audio inputs, and trained on permissively licensed music data. A2SB is capable of achieving state-of-the-art bandwidth extension and inpainting quality on several out-of-distribution music test sets. Our demo website is https: //research.nvidia.com/labs/adlr/A2SB/.
Reducing the bandwidth of speech is common practice in resource constrained environments like low-bandwidth speech transmission or low-complexity vocoding. We propose a lightweight and robust method for extending the bandwidth of wideband speech signals that is inspired by classical methods developed in the speech coding context. The resulting model has just $\sim 370$~K parameters and a complexity of ~140 MFLOPS (or ~70 MMACS). With a frame size of 10 ms and a lookahead of just 0.27 ms the model is well-suited for common wideband speech codecs. We evaluate the model's robustness by pairing it with the Opus SILK speech codec (1.5 release) and verify in a P.808 DCR listening test that it significantly improves quality from 6 to 12 kb/s. We also demonstrate that Opus 1.5 together with the proposed bandwidth extension at 9 kb/s meets the quality of 3GPP EVS at 9.6 kb/s and that of Opus 1.4 at 18 kb/s showing that the blind bandwidth extension can meet the quality of classical guided bandwidth extensions.
This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for time-domain signal reconstruction. As a result, our model simplifies the synthesis process and removes the quality upper-bound introduced by any mel-spectrogram vocoder compared to prior work SpeechFlow. The proposed method is evaluated on multiple speech restoration tasks, including speech denoising, bandwidth extension, codec artifact removal, and target speaker extraction. In all scenarios, finetuning our pretrained model results in superior performance over strong baselines. Notably, in the target speaker extraction task, our model outperforms existing systems, including those leveraging SSL-pretrained encoders like WavLM. The code and the pretrained checkpoints are publicly available in the NVIDIA NeMo framework.
Noise suppression (NS) algorithms are effective in improving speech quality in many cases. However, aggressive noise suppression can damage the target speech, reducing both speech intelligibility and quality despite removing the noise. This study proposes an explicit speech restoration method using a voice conversion (VC) technique for restoration after noise suppression. We observed that high-quality speech can be restored through a diffusion-based voice conversion stage, conditioned on the target speaker embedding and speech content information extracted from the de-noised speech. This speech restoration can achieve enhancement effects such as bandwidth extension, de-reverberation, and in-painting. Our experimental results demonstrate that this two-stage NS+VC framework outperforms single-stage enhancement models in terms of output speech quality, as measured by objective metrics, while scoring slightly lower in speech intelligibility. To further improve the intelligibility of the combined system, we propose a content encoder adaptation method for robust content extraction in noisy conditions.
In this paper, we propose a dual-stage architecture for bandwidth extension (BWE) increasing the effective sampling rate of speech signals from 8 kHz to 48 kHz. Unlike existing end-to-end deep learning models, our proposed method explicitly models BWE using excitation and linear time-varying (LTV) filter stages. The excitation stage broadens the spectrum of the input, while the filtering stage properly shapes it based on outputs from an acoustic feature predictor. To this end, an acoustic feature loss term can implicitly promote the excitation subnetwork to produce white spectra in the upper frequency band to be synthesized. Experimental results demonstrate that the added inductive bias provided by our approach can improve upon BWE results using the generators from both SEANet or HiFi-GAN as exciters, and that our means of adapting processing with acoustic feature predictions is more effective than that used in HiFi-GAN-2. Secondary contributions include extensions of the SEANet model to accommodate local conditioning information, as well as the application of HiFi-GAN-2 for the BWE problem.
Vibravox is a dataset compliant with the General Data Protection Regulation (GDPR) containing audio recordings using five different body-conduction audio sensors: two in-ear microphones, two bone conduction vibration pickups, and a laryngophone. The dataset also includes audio data from an airborne microphone used as a reference. The Vibravox corpus contains 45 hours per sensor of speech samples and physiological sounds recorded by 188 participants under different acoustic conditions imposed by a high order ambisonics 3D spatializer. Annotations about the recording conditions and linguistic transcriptions are also included in the corpus. We conducted a series of experiments on various speech-related tasks, including speech recognition, speech enhancement, and speaker verification. These experiments were carried out using state-of-the-art models to evaluate and compare their performances on signals captured by the different audio sensors offered by the Vibravox dataset, with the aim of gaining a better grasp of their individual characteristics.
The last decade has witnessed significant advancements in deep learning-based speech enhancement (SE). However, most existing SE research has limitations on the coverage of SE sub-tasks, data diversity and amount, and evaluation metrics. To fill this gap and promote research toward universal SE, we establish a new SE challenge, named URGENT, to focus on the universality, robustness, and generalizability of SE. We aim to extend the SE definition to cover different sub-tasks to explore the limits of SE models, starting from denoising, dereverberation, bandwidth extension, and declipping. A novel framework is proposed to unify all these sub-tasks in a single model, allowing the use of all existing SE approaches. We collected public speech and noise data from different domains to construct diverse evaluation data. Finally, we discuss the insights gained from our preliminary baseline experiments based on both generative and discriminative SE methods with 12 curated metrics.
The majority of existing speech bandwidth extension (BWE) methods operate under the constraint of fixed source and target sampling rates, which limits their flexibility in practical applications. In this paper, we propose a multi-stage speech BWE model named MS-BWE, which can handle a set of source and target sampling rate pairs and achieve flexible extensions of frequency bandwidth. The proposed MS-BWE model comprises a cascade of BWE blocks, with each block featuring a dual-stream architecture to realize amplitude and phase extension, progressively painting the speech frequency bands stage by stage. The teacher-forcing strategy is employed to mitigate the discrepancy between training and inference. Experimental results demonstrate that our proposed MS-BWE is comparable to state-of-the-art speech BWE methods in speech quality. Regarding generation efficiency, the one-stage generation of MS-BWE can achieve over one thousand times real-time on GPU and about sixty times on CPU.
This paper presents a novel approach to audio restoration, focusing on the enhancement of low-quality music recordings, and in particular historical ones. Building upon a previous algorithm called BABE, or Blind Audio Bandwidth Extension, we introduce BABE-2, which presents a series of improvements. This research broadens the concept of bandwidth extension to \emph{generative equalization}, a novel task that, to the best of our knowledge, has not been explicitly addressed in previous studies. BABE-2 is built around an optimization algorithm utilizing priors from diffusion models, which are trained or fine-tuned using a curated set of high-quality music tracks. The algorithm simultaneously performs two critical tasks: estimation of the filter degradation magnitude response and hallucination of the restored audio. The proposed method is objectively evaluated on historical piano recordings, showing an enhancement over the prior version. The method yields similarly impressive results in rejuvenating the works of renowned vocalists Enrico Caruso and Nellie Melba. This research represents an advancement in the practical restoration of historical music.
Speech bandwidth extension (BWE) refers to widening the frequency bandwidth range of speech signals, enhancing the speech quality towards brighter and fuller. This paper proposes a generative adversarial network (GAN) based BWE model with parallel prediction of Amplitude and Phase spectra, named AP-BWE, which achieves both high-quality and efficient wideband speech waveform generation. The proposed AP-BWE generator is entirely based on convolutional neural networks (CNNs). It features a dual-stream architecture with mutual interaction, where the amplitude stream and the phase stream communicate with each other and respectively extend the high-frequency components from the input narrowband amplitude and phase spectra. To improve the naturalness of the extended speech signals, we employ a multi-period discriminator at the waveform level and design a pair of multi-resolution amplitude and phase discriminators at the spectral level, respectively. Experimental results demonstrate that our proposed AP-BWE achieves state-of-the-art performance in terms of speech quality for BWE tasks targeting sampling rates of both 16 kHz and 48 kHz. In terms of generation efficiency, due to the all-convolutional architecture and all-frame-level operations, the proposed AP-BWE can generate 48 kHz waveform samples 292.3 times faster than real-time on a single RTX 4090 GPU and 18.1 times faster than real-time on a single CPU. Notably, to our knowledge, AP-BWE is the first to achieve the direct extension of the high-frequency phase spectrum, which is beneficial for improving the effectiveness of existing BWE methods.
Many hearables contain an in-ear microphone, which may be used to capture the own voice of its user in noisy environments. Since the in-ear microphone mostly records body-conducted speech due to ear canal occlusion, it suffers from band-limitation effects while only capturing a limited amount of external noise. To enhance the quality of the in-ear microphone signal using algorithms aiming at joint bandwidth extension, equalization, and noise reduction, it is desirable to have an accurate model of the own voice transfer characteristics between the entrance of the ear canal and the in-ear microphone. Such a model can be used, e.g., to simulate a large amount of in-ear recordings to train supervised learning-based algorithms. Since previous research on ear canal occlusion suggests that own voice transfer characteristics depend on speech content, in this contribution we propose a speech-dependent system identification model based on phoneme recognition. We assess the accuracy of simulating own voice speech by speech-dependent and speech-independent modeling and investigate how well modeling approaches are able to generalize to different talkers. Simulation results show that using the proposed speech-dependent model is preferable for simulating in-ear recordings compared to using a speech-independent model.
Restoring degraded music signals is essential to enhance audio quality for downstream music manipulation. Recent diffusion-based music restoration methods have demonstrated impressive performance, and among them, diffusion posterior sampling (DPS) stands out given its intrinsic properties, making it versatile across various restoration tasks. In this paper, we identify that there are potential issues which will degrade current DPS-based methods' performance and introduce the way to mitigate the issues inspired by diverse diffusion guidance techniques including the RePaint (RP) strategy and the Pseudoinverse-Guided Diffusion Models ($\Pi$GDM). We demonstrate our methods for the vocal declipping and bandwidth extension tasks under various levels of distortion and cutoff frequency, respectively. In both tasks, our methods outperform the current DPS-based music restoration benchmarks. We refer to \url{http://carlosholivan.github.io/demos/audio-restoration-2023.html} for examples of the restored audio samples.
Phase information has a significant impact on speech perceptual quality and intelligibility. However, existing speech enhancement methods encounter limitations in explicit phase estimation due to the non-structural nature and wrapping characteristics of the phase, leading to a bottleneck in enhanced speech quality. To overcome the above issue, in this paper, we proposed MP-SENet, a novel Speech Enhancement Network that explicitly enhances Magnitude and Phase spectra in parallel. The proposed MP-SENet comprises a Transformer-embedded encoder-decoder architecture. The encoder aims to encode the input distorted magnitude and phase spectra into time-frequency representations, which are further fed into time-frequency Transformers for alternatively capturing time and frequency dependencies. The decoder comprises a magnitude mask decoder and a phase decoder, directly enhancing magnitude and wrapped phase spectra by incorporating a magnitude masking architecture and a phase parallel estimation architecture, respectively. Multi-level loss functions explicitly defined on the magnitude spectra, wrapped phase spectra, and short-time complex spectra are adopted to jointly train the MP-SENet model. A metric discriminator is further employed to compensate for the incomplete correlation between these losses and human auditory perception. Experimental results demonstrate that our proposed MP-SENet achieves state-of-the-art performance across multiple speech enhancement tasks, including speech denoising, dereverberation, and bandwidth extension. Compared to existing phase-aware speech enhancement methods, it further mitigates the compensation effect between the magnitude and phase by explicit phase estimation, elevating the perceptual quality of enhanced speech.
Perceptual audio quality measurement systems algorithmically analyze the output of audio processing systems to estimate possible perceived quality degradation using perceptual models of human audition. In this manner, they save the time and resources associated with the design and execution of listening tests (LTs). Models of disturbance audibility predicting peripheral auditory masking in quality measurement systems have considerably increased subjective quality prediction performance of signals processed by perceptual audio codecs. Additionally, cognitive effects have also been known to regulate perceived distortion severity by influencing their salience. However, the performance gains due to cognitive effect models in quality measurement systems were inconsistent so far, particularly for music signals. Firstly, this paper presents an improved model of informational masking (IM) -- an important cognitive effect in quality perception -- that considers disturbance information complexity around the masking threshold. Secondly, we incorporate the proposed IM metric into a quality measurement systems using a novel interaction analysis procedure between cognitive effects and distortion metrics. The procedure establishes interactions between cognitive effects and distortion metrics using LT data. The proposed IM metric is shown to outperform previously proposed IM metrics in a validation task against subjective quality scores from large and diverse LT databases. Particularly, the proposed system showed an increased quality prediction of music signals coded with bandwidth extension techniques, where other models frequently fail.
Audio bandwidth extension involves the realistic reconstruction of high-frequency spectra from bandlimited observations. In cases where the lowpass degradation is unknown, such as in restoring historical audio recordings, this becomes a blind problem. This paper introduces a novel method called BABE (Blind Audio Bandwidth Extension) that addresses the blind problem in a zero-shot setting, leveraging the generative priors of a pre-trained unconditional diffusion model. During the inference process, BABE utilizes a generalized version of diffusion posterior sampling, where the degradation operator is unknown but parametrized and inferred iteratively. The performance of the proposed method is evaluated using objective and subjective metrics, and the results show that BABE surpasses state-of-the-art blind bandwidth extension baselines and achieves competitive performance compared to informed methods when tested with synthetic data. Moreover, BABE exhibits robust generalization capabilities when enhancing real historical recordings, effectively reconstructing the missing high-frequency content while maintaining coherence with the original recording. Subjective preference tests confirm that BABE significantly improves the audio quality of historical music recordings. Examples of historical recordings restored with the proposed method are available on the companion webpage: (http://research.spa.aalto.fi/publications/papers/ieee-taslp-babe/)