Related papers: Towards end-to-end F0 voice conversion based on Du…

Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring…

Emotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity. Prior studies show that it is possible to disentangle emotional prosody using an encoder-decoder network…

In this paper, we present an end-to-end approach for environmental sound classification based on a 1D Convolution Neural Network (CNN) that learns a representation directly from the audio signal. Several convolutional layers are used to…

A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer. Recently, methods that leverage self-supervised audio representations such as HuBERT and Wav2Vec 2.0 have helped…

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…

For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer learning and adaptation…

Machine recognition of an atypical speech like whispered speech, is a challenging task. We introduce whisper-to-natural-speech conversion using sequence-to-sequence approach by proposing enhanced transformer architecture, which uses both…

State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we study end-to-end systems trained directly from the raw…

End-to-end models have gradually become the main technical stream for voice trigger, aiming to achieve an utmost prediction accuracy but with a small footprint. In present paper, we propose an end-to-end voice trigger framework, namely…

In this paper, we present FaceTuneGAN, a new 3D face model representation decomposing and encoding separately facial identity and facial expression. We propose a first adaptation of image-to-image translation networks, that have…

Machine learning approaches to auditory object recognition are traditionally based on engineered features such as those derived from the spectrum or cepstrum. More recently, end-to-end classification systems in image and auditory…

Previous studies have demonstrated that end-to-end learning enables significant shaping gains over additive white Gaussian noise (AWGN) channels. However, its benefits have not yet been quantified over realistic wireless channel models.…

We propose a learnable content adaptive front end for audio signal processing. Before the modern advent of deep learning, we used fixed representation non-learnable front-ends like spectrogram or mel-spectrogram with/without neural…

Although current face manipulation techniques achieve impressive performance regarding quality and controllability, they are struggling to generate temporal coherent face videos. In this work, we explore to take full advantage of the…

Emotional Voice Conversion (EVC) aims to convert the emotional style of a source speech signal to a target style while preserving its content and speaker identity information. Previous emotional conversion studies do not disentangle…

Recently advancements in deep learning allowed the development of end-to-end trained goal-oriented dialog systems. Although these systems already achieve good performance, some simplifications limit their usage in real-life scenarios. In…

In this paper, we explore the encoding/pooling layer and loss function in the end-to-end speaker and language recognition system. First, a unified and interpretable end-to-end system for both speaker and language recognition is developed.…

A novel end-to-end binaural sound localisation approach is proposed which estimates the azimuth of a sound source directly from the waveform. Instead of employing hand-crafted features commonly employed for binaural sound localisation, such…

Convolutional neural networks are able to perform a hierarchical learning process starting with local features. However, a limited attention is paid to enhancing such elementary level features like edges. We propose and evaluate two…

The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal. Recently, various studies have focused on this task and have achieved promising performance. However, current speech-to-image…