Related papers: Mel-spectrogram augmentation for sequence to seque…

Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching…

Sequential recommender systems have recently achieved significant performance improvements with the exploitation of deep learning (DL) based methods. However, although various DL-based methods have been introduced, most of them only focus…

Environmental sound classification (ESC) has gained significant attention due to its diverse applications in smart city monitoring, fault detection, acoustic surveillance, and manufacturing quality control. To enhance CNN performance,…

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave…

Motivated by the attention mechanism of the human visual system and recent developments in the field of machine translation, we introduce our attention-based and recurrent sequence to sequence autoencoders for fully unsupervised…

We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrogram prediction mechanism where the system first predicts…

Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that…

This work introduces sequential neural beamforming, which alternates between neural network based spectral separation and beamforming based spatial separation. Our neural networks for separation use an advanced convolutional architecture…

Recently, mainstream mel-spectrogram-based neural vocoders rely on generative adversarial network (GAN) for high-fidelity speech generation, e.g., HiFi-GAN and BigVGAN. However, the use of GAN restricts training efficiency and model…

Self-supervised learning (SSL) has proven vital in speech and audio-related applications. The paradigm trains a general model on unlabeled data that can later be used to solve specific downstream tasks. This type of model is costly to train…

In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vocoder is increasing. A mel-spectrogram vocoder must solve…

Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are…

Speech Emotion Recognition (SER) traditionally relies on auditory data analysis for emotion classification. Several studies have adopted different methods for SER. However, existing SER methods often struggle to capture subtle emotional…

Singing voice conversion (SVC) aims to convert the voice of one singer to that of other singers while keeping the singing content and melody. On top of recent voice conversion works, we propose a novel model to steadily convert songs while…

Integrating an external language model into a sequence-to-sequence speech recognition system is non-trivial. Previous works utilize linear interpolation or a fusion network to integrate external language models. However, these approaches…

The process of reconstructing missing parts of speech audio from context is called speech in-painting. Human perception of speech is inherently multi-modal, involving both audio and visual (AV) cues. In this paper, we introduce and study a…

In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network engineering and classification tasks. The idea here is to…

Analysing music in the field of machine learning is a very difficult problem with numerous constraints to consider. The nature of audio data, with its very high dimensionality and widely varying scales of structure, is one of the primary…

Video-to-speech synthesis is the task of reconstructing the speech signal from a silent video of a speaker. Most established approaches to date involve a two-step process, whereby an intermediate representation from the video, such as a…

Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM), pronunciation (PM) and language (LM) models into a single…