Related papers: Synthesizer Sound Matching Using Audio Spectrogram…
The rise of deep learning algorithms has led many researchers to withdraw from using classic signal processing methods for sound generation. Deep learning models have achieved expressive voice synthesis, realistic sound textures, and…
We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre.…
This paper presents a high quality singing synthesizer that is able to model a voice with limited available recordings. Based on the sequence-to-sequence singing model, we design a multi-singer framework to leverage all the existing singing…
Learning robust audio representations currently demands extensive datasets of real-world sound recordings. By applying artificial transformations to these recordings, models can learn to recognize similarities despite subtle variations…
We propose a semi-supervised singing synthesizer, which is able to learn new voices from audio data only, without any annotations such as phonetic segmentation. Our system is an encoder-decoder model with two encoders, linguistic and…
A new framework is presented for generating musical audio using autoencoder neural networks. With the presented framework, called network modulation synthesis, users can create synthesis architectures and use novel generative algorithms to…
Acoustic matching aims to re-synthesize an audio clip to sound as if it were recorded in a target acoustic environment. Existing methods assume access to paired training data, where the audio is observed in both source and target…
We present a deep neural network-based methodology for synthesising percussive sounds with control over high-level timbral characteristics of the sounds. This approach allows for intuitive control of a synthesizer, enabling the user to…
A sound field synthesis method enhancing perceptual quality is proposed. Sound field synthesis using multiple loudspeakers enables spatial audio reproduction with a broad listening area; however, synthesis errors at high frequencies called…
Speech Language Models (SLMs) have recently emerged as a unified paradigm for addressing a wide range of speech-related tasks, including text-to-speech (TTS), speech enhancement (SE), and automatic speech recognition (ASR). However, the…
Most recent speech synthesis systems are composed of a synthesizer and a vocoder. However, the existing synthesizers and vocoders can only be matched to acoustic features extracted with a specific configuration. Hence, we can't combine…
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions.…
Modulations are a critical part of sound design and music production, enabling the creation of complex and evolving audio. Modern synthesizers provide envelopes, low frequency oscillators (LFOs), and more parameter automation tools that…
Deep learning appears as an appealing solution for Automatic Synthesizer Programming (ASP), which aims to assist musicians and sound designers in programming sound synthesizers. However, integrating software synthesizers into training…
Recent neural waveform synthesizers such as WaveNet, WaveGlow, and the neural-source-filter (NSF) model have shown good performance in speech synthesis despite their different methods of waveform generation. The similarity between speech…
Audio-to-score alignment is a long-standing challenge in music information retrieval and arguably the most widely applicable alignment task for music research. Alignment algorithms match two versions of a piece of music, and for this to…
An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string synthesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to capture variance not explained…
Numerous models have shown great success in the fields of speech recognition as well as speech synthesis, but models for speech to speech processing have not been heavily explored. We propose Speech to Speech Synthesis Network (STSSN), a…
Use a parametric representation of audio to train a generative model in the interest of obtaining more flexible control over the generated sound.
An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string synthesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to capture variance not explained…