Related papers: Towards zero-shot amplifier modeling: One-to-many …

Audio representation learning based on deep neural networks (DNNs) emerged as an alternative approach to hand-crafted features. For achieving high performance, DNNs often need a large amount of annotated data which can be difficult and…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Deep learning has become a standard approach for the modeling of audio effects, yet strictly black-box modeling remains problematic for time-varying systems. Unlike time-invariant effects, training models on devices with internal modulation…

Deep generative models are now able to synthesize high-quality audio signals, shifting the critical aspect in their development from audio quality to control capabilities. Although text-to-music generation is getting largely adopted by the…

A crucial aspect for the successful deployment of audio-based models "in-the-wild" is the robustness to the transformations introduced by heterogeneous acquisition conditions. In this work, we propose a method to perform one-shot microphone…

Neural network models for guitar amplifier emulation, while being effective, often demand high computational cost and lack interpretability. Drawing ideas from physical amplifier design, this paper aims to address these issues with a new…

Telecommunication networks make extensive use of power amplifiers to broaden the coverage from transmitter to receiver. Achieving high power efficiency is challenging and comes at a price: the wanted linear performance is degraded due to…

Model fusion seeks to combine independently trained neural networks into a single model without retraining, but is complicated by representational divergence arising from permutation invariance, random initialization, and heterogeneous…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

Timbre and pitch are the two main perceptual properties of musical sounds. Depending on the target applications, we sometimes prefer to focus on one of them, while reducing the effect of the other. Researchers have managed to hand-craft…

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…

We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method augments the state-of-the-art bilinear compatibility model…

Traditional studies on voice conversion (VC) have made progress with parallel training data and known speakers. Good voice conversion quality is obtained by exploring better alignment modules or expressive mapping functions. In this study,…

Zero-shot audio classification aims to recognize and classify a sound class that the model has never seen during training. This paper presents a novel approach for zero-shot audio classification using automatically generated sound attribute…

Audio texture manipulation involves modifying the perceptual characteristics of a sound to achieve specific transformations, such as adding, removing, or replacing auditory elements. In this paper, we propose an exemplar-based analogy model…

The end-to-end speech synthesis model can directly take an utterance as reference audio, and generate speech from the text with prosody and speaker characteristics similar to the reference audio. However, an appropriate acoustic embedding…

Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in finding a good representation for the current…

While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we propose a novel end-to-end trained transformer model which is…

Within numerical reasoning, understanding numbers themselves is still a challenge for existing language models. Simple generalisations, such as solving 100+200 instead of 1+2, can substantially affect model performance (Sivakumar and…

In this paper, we present a framework for contrastive learning for audio representations, in a self supervised frame work without access to any ground truth labels. The core idea in self supervised contrastive learning is to map an audio…