Related papers: A Neural Parametric Singing Synthesizer
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses linear prediction to significantly reduce the complexity of…
This paper introduces a novel data-driven strategy for synthesizing gramophone noise audio textures. A diffusion probabilistic model is applied to generate highly realistic quasiperiodic noises. The proposed model is designed to generate…
A music mashup combines audio elements from two or more songs to create a new work. To reduce the time and effort required to make them, researchers have developed algorithms that predict the compatibility of audio elements. Prior work has…
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…
Entertainment-oriented singing voice synthesis (SVS) requires a vocoder to generate high-fidelity (e.g. 48kHz) audio. However, most text-to-speech (TTS) vocoders cannot reconstruct the waveform well in this scenario. In this paper, we…
There are many use cases in singing synthesis where creating voices from small amounts of data is desirable. In text-to-speech there have been several promising results that apply voice cloning techniques to modern deep learning based…
In this paper, we propose an online speaker adaptation method for WaveNet-based neural vocoders in order to improve their performance on speaker-independent waveform generation. In this method, a speaker encoder is first constructed using a…
The goal of this contribution is to use a parametric speech synthesis system for reducing background noise and other interferences from recorded speech signals. In a first step, Hidden Markov Models of the synthesis system are trained. Two…
Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence. Autoregressive models, such as WaveNet, model local structure at the…
Neural vocoders are now being used in a wide range of speech processing applications. In many of those applications, the vocoder can be the most complex component, so finding lower complexity algorithms can lead to significant practical…
Deep learning based singing voice synthesis (SVS) systems have been demonstrated to flexibly generate singing with better qualities, compared to conventional statistical parametric based methods. However, neural systems are generally…
Singing Voice Synthesis (SVS) remains constrained in practical deployment due to its strong dependence on accurate phoneme-level alignment and manually annotated melody contours, requirements that are resource-intensive and hinder…
The traditional songwriting process is rather complex and this is evident in the time it takes to produce lyrics that fit the genre and form comprehensive verses. Our project aims to simplify this process with deep learning techniques, thus…
The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the…
In this paper, we present a machine-learning approach to pitch correction for voice in a karaoke setting, where the vocals and accompaniment are on separate tracks and time-aligned. The network takes as input the time-frequency…
This Ph.D. thesis focuses on developing a system for high-quality speech synthesis and voice conversion. Vocoder-based speech analysis, manipulation, and synthesis plays a crucial role in various kinds of statistical parametric speech…
This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian…
Song generation focuses on producing controllable high-quality songs based on various prompts. However, existing methods struggle to generate vocals and accompaniments with prompt-based control and proper alignment. Additionally, they fall…
Autoregressive models are typically applied to sequences of discrete tokens, but recent research indicates that generating sequences of continuous embeddings in an autoregressive manner is also feasible. However, such Continuous…
In this paper, we propose a method of speaker adaption with intuitive prosodic features for statistical parametric speech synthesis. The intuitive prosodic features employed in this method include pitch, pitch range, speech rate and energy…