Related papers: Learning Vocal-Tract Area and Radiation with a Phy…

In this paper, we present a vocoder-free framework for audio super-resolution that employs a flow matching generative model to capture the conditional distribution of complex-valued spectral coefficients. Unlike conventional two-stage…

Neural vocoders are central to speech synthesis; despite their success, most still suffer from limited prosody modeling and inaccurate phase reconstruction. We propose a vocoder that introduces prosody-guided harmonic attention to enhance…

We introduce a new dataset for training and evaluating grounded language models. Our data is collected within a virtual reality environment and is designed to emulate the quality of language data to which a pre-verbal child is likely to…

This paper addresses the limitations of Physics-Informed Neural Networks for time-dependent problems by introducing a tangent bundle learning framework. Instead of directly approximating the solution, we parameterize its temporal derivative…

Physical models of rigid bodies are used for sound synthesis in applications from virtual environments to music production. Traditional methods such as modal synthesis often rely on computationally expensive numerical solvers, while recent…

Detecting sound source objects within visual observation is important for autonomous robots to comprehend surrounding environments. Since sounding objects have a large variety with different appearances in our living environments, labeling…

In this study, we propose the global context guided channel and time-frequency transformations to model the long-range, non-local time-frequency dependencies and channel variances in speaker representations. We use the global context…

Recently, deep representation learning has shown strong performance in multiple audio tasks. However, its use for learning spatial representations from multichannel audio is underexplored. We investigate the use of a pretraining stage based…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

This paper addresses the challenge of speaker separation, which remains an active research topic despite the promising results achieved in recent years. These results, however, often degrade in real recording conditions due to the presence…

The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in…

With the rapid development of neural network architectures and speech processing models, singing voice synthesis with neural networks is becoming the cutting-edge technique of digital music production. In this work, in order to explore how…

Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a…

Neural vocoders have recently advanced waveform generation, yielding natural and expressive audio. Among these approaches, iSTFT-based vocoders have recently gained attention. They predict a complex-valued spectrogram and then synthesize…

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

In text-to-speech (TTS) and voice conversion (VC), acoustic features, such as mel spectrograms, are typically used as synthesis or conversion targets owing to their compactness and ease of learning. However, because the ultimate goal is to…

In this paper, we propose a model to perform style transfer of speech to singing voice. Contrary to the previous signal processing-based methods, which require high-quality singing templates or phoneme synchronization, we explore a…

In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…

Separating vocal elements from musical tracks is a longstanding challenge in audio signal processing. This study tackles the distinct separation of vocal components from musical spectrograms. We employ the Short Time Fourier Transform…

Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect…