Paper Archive

A Head-Related Transfer Function (HRTF) is able to capture alterations a sound wave undergoes from its source before it reaches the entrances of a listener’s left and right ear canals, and is imperative for creating immersive experiences in virtual and augmented reality (VR/AR). Nevertheless, creating personalized HRTFs demands sophisticated equipment and is hindered by time-consuming data acquisition processes. To counteract these challenges, various techniques for HRTF interpolation and up-sampling have been proposed. This paper illustrates how Generative Adversarial Networks (GANs) can be applied to HRTF data upsampling in the spherical harmonics domain. We propose using Autoencoding Generative Adversarial Networks (AE-GAN) to upsample lowdegree spherical harmonics coefficients and get a more accurate representation of the full HRTF set. The proposed method is benchmarked against two baselines: barycentric interpolation and HRTF selection. Results from log-spectral distortion (LSD) evaluation suggest that the proposed AE-GAN has significant potential for upsampling very sparse HRTFs, achieving 17% improvement over baseline methods.

Download

Virtual Analog (VA) modeling aims to simulate the behavior of hardware circuits via algorithms to replicate their tone digitally. Dynamic Range Compressor (DRC) is an audio processing module that controls the dynamics of a track by reducing and amplifying the volumes of loud and quiet sounds, which is essential in music production. In recent years, neural-network-based VA modeling has shown great potential in producing high-fidelity models. However, due to the lack of data quantity and diversity, their generalization ability in different parameter settings and input sounds is still limited. To tackle this problem, we present Solid State Bus-Comp, the first large-scale and diverse dataset for modeling the classical VCA compressor — SSL 500 G-Bus. Specifically, we manually collected 175 unmastered songs from the Cambridge Multitrack Library. We recorded the compressed audio in 220 parameter combinations, resulting in an extensive 2528-hour dataset with diverse genres, instruments, tempos, and keys. Moreover, to facilitate the use of our proposed dataset, we conducted benchmark experiments in various open-sourced black-box and grey-box models, as well as white-box plugins. We also conducted ablation studies in different data subsets to illustrate the effectiveness of the improved data diversity and quantity. The dataset and demos are on our project page: https: //www.yichenggu.com/SolidStateBusComp/.

Download

The increasing demand for high-quality digital emulations of analog audio hardware, such as vintage tube guitar amplifiers, led to numerous works on neural network-based black-box modeling, with deep learning architectures like WaveNet showing promising results. However, a key limitation in all of these models was the aliasing artifacts stemming from nonlinear activation functions in neural networks. In this paper, we investigated novel and modified activation functions aimed at mitigating aliasing within neural amplifier models. Supporting this, we introduced a novel metric, the Aliasing-to-Signal Ratio (ASR), which quantitatively assesses the level of aliasing with high accuracy. Measuring also the conventional Error-to-Signal Ratio (ESR), we conducted studies on a range of preexisting and modern activation functions with varying stretch factors. Our findings confirmed that activation functions with smoother curves tend to achieve lower ASR values, indicating a noticeable reduction in aliasing. Notably, this improvement in aliasing reduction was achievable without a substantial increase in ESR, demonstrating the potential for high modeling accuracy with reduced aliasing in neural amp models.

Download

This paper investigates the optimization of Truncated Backpropagation Through Time (TBPTT) for training neural networks in digital audio effect modeling, with a focus on dynamic range compression. The study evaluates key TBPTT hyperparameters – sequence number, batch size, and sequence length – and their influence on model performance. Using a convolutional-recurrent architecture, we conduct extensive experiments across datasets with and without conditioning by user controls. Results demonstrate that carefully tuning these parameters enhances model accuracy and training stability, while also reducing computational demands. Objective evaluations confirm improved performance with optimized settings, while subjective listening tests indicate that the revised TBPTT configuration maintains high perceptual quality.

Download

Articulatory features can provide interpretable and flexible controls for the synthesis of human vocalizations by allowing the user to directly modify parameters like vocal strain or lip position. To make this manipulation through resynthesis possible, we need to estimate the features that result in a desired vocalization directly from audio recordings. In this work, we propose a white-box optimization technique for estimating glottal source parameters and vocal tract shapes from audio recordings of human vowels. The approach is based on inverse filtering and optimizing the frequency response of a waveguide model of the vocal tract with gradient descent, propagating error gradients through the mapping of articulatory features to the vocal tract area function. We apply this method to the task of matching the sound of the Pink Trombone, an interactive articulatory synthesizer, to a given vocalization. We find that our method accurately recovers control functions for audio generated by the Pink Trombone itself. We then compare our technique against evolutionary optimization algorithms and a neural network trained to predict control parameters from audio. A subjective evaluation finds that our approach outperforms these black-box optimization baselines on the task of reproducing human vocalizations.

Download

Piano transcription is a classic problem in music information retrieval. More and more transcription methods based on deep learning have been proposed in recent years. In 2019, Google Brain published a larger piano transcription dataset, MAESTRO. On this dataset, Onsets and Frames transcription approach proposed by Hawthorne achieved a stunning onset F1 score of 94.73%. Unlike the annotation method of Onsets and Frames, Transition-aware model presented in this paper annotates the attack process of piano signals called atack transition in multiple frames, instead of only marking the onset frame. In this way, the piano signals around onset time are taken into account, enabling the detection of piano onset more stable and robust. Transition-aware achieves a higher transcription F1 score than Onsets and Frames on MAESTRO dataset and MAPS dataset, reducing many extra note detection errors. This indicates that Transition-aware approach has better generalization ability on different datasets.

Download

This paper describes a new onset-informed source separation method based on non-negative matrix factorization (NMF) with binary masks. Many previous approaches to separate a target instrument sound from polyphonic music have used side-information of the target that is time-consuming to prepare. The proposed method leverages the onsets of the target instrument sound to facilitate separation. Onsets are useful information that users can easily generate by tapping while listening to the target in music. To utilize onsets in NMF-based sound source separation, we introduce binary masks that represent on/off states of the target sound. Binary masks are formulated as Markov chains based on continuity of musical instrument sound. Owing to the binary masks, onsets can be handled as a time frame in which the binary masks change from off to on state. The proposed model is inferred by Gibbs sampling, in which the target sound source can be sampled efficiently by using its onsets. We conducted experiments to separate the target melody instrument from recorded polyphonic music. Separation results showed about 2 to 10 dB improvement in target source to residual noise ratio compared to the polyphonic sound. When some onsets were missed or deviated, the method is still effective for target sound source separation.

Download

Object-based audio production requires the positional metadata to be defined for each point-source object, including the key elements in the foreground of the sound scene. In many media production use cases, both cameras and microphones are employed to make recordings, and the human voice is often a key element. In this research, we detect and locate the active speaker in the video, facilitating the automatic extraction of the positional metadata of the talker relative to the camera’s reference frame. With the integration of the visual modality, this study expands upon our previous investigation focused solely on audio-based active speaker detection and localization. Our experiments compare conventional audio-visual approaches for active speaker detection that leverage monaural audio, our previous audio-only method that leverages multichannel recordings from a microphone array, and a novel audio-visual approach integrating vision and multichannel audio. We found the role of the two modalities to complement each other. Multichannel audio, overcoming the problem of visual occlusions, provides a double-digit reduction in detection error compared to audio-visual methods with single-channel audio. The combination of multichannel audio and vision further enhances spatial accuracy, leading to a four-percentage point increase in F1 score on the Tragic Talkers dataset. Future investigations will assess the robustness of the model in noisy and highly reverberant environments, as well as tackle the problem of off-screen speakers.

Download

In this paper, we propose the use of real-valued Linear Recurrent Units (LRUs) for black-box modeling of audio circuits. A network architecture composed of real LRU blocks interleaved with nonlinear processing stages is proposed. Two case studies are presented, a second-order diode clipper and an overdrive distortion pedal. Furthermore, we show how to integrate the antiderivative antialiaisng technique into the proposed method, effectively lowering oversampling requirements. Our experiments show that the proposed method generates models that accurately capture the nonlinear dynamics of the examined devices and are highly efficient, which makes them suitable for real-time operation inside Digital Audio Workstations.

Download

This paper proposes a neural network for carrying out parametric equalizer (EQ) matching. The novelty of this neural network solution is that it can be optimized directly in the frequency domain by means of differentiable biquads, rather than relying solely on a loss on parameter values which does not correlate directly with the system output. We compare the performance of the proposed neural network approach with that of a baseline algorithm based on a convex relaxation of the problem. It is observed that the neural network can provide better matching than the baseline approach because it directly attempts to solve the non-convex problem. Moreover, we show that the same network trained with only a parameter loss is insufficient for the task, despite the fact that it matches underlying EQ parameters better than one trained with a combination of spectral and parameter losses.

Download