Related papers: Mel Spectrogram Inversion with Stable Pitch

Many music theoretical constructs (such as scale types, modes, cadences, and chord types) are defined in terms of pitch intervals---relative distances between pitches. Therefore, when computer models are employed in music tasks, it can be…

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…

Changing the vocal tract shape is one of the techniques which can be used by the players of wind instruments to modify the quality of the sound. It has been intensely studied in the case of reed instruments but has received only little…

Introducing variability while maintaining coherence is a core task in learning to generate utterances in conversation. Standard neural encoder-decoder models and their extensions using conditional variational autoencoder often result in…

When convolutional neural networks are used to tackle learning problems based on music or, more generally, time series data, raw one-dimensional data are commonly pre-processed to obtain spectrogram or mel-spectrogram coefficients, which…

Previously, we introduced VoiceGrad, a nonparallel voice conversion (VC) technique enabling mel-spectrogram conversion from source to target speakers using a score-based diffusion model. The concept involves training a score network to…

In deep learning research, many melody extraction models rely on redesigning neural network architectures to improve performance. In this paper, we propose an input feature modification and a training objective modification based on two…

Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…

Recently, autoregressive neural vocoders have provided remarkable performance in generating high-fidelity speech and have been able to produce synthetic speech in real-time. However, autoregressive neural vocoders such as WaveFlow are…

Recent progress in deep generative models has improved the quality of neural vocoders in speech domain. However, generating a high-quality singing voice remains challenging due to a wider variety of musical expressions in pitch, loudness,…

In recent years, neural vocoders have surpassed classical speech generation approaches in naturalness and perceptual quality of the synthesized speech. Computationally heavy models like WaveNet and WaveGlow achieve best results, while…

Maximum Voiced Frequency (MVF) is used in various speech models as the spectral boundary separating periodic and aperiodic components during the production of voiced sounds. Recent studies have shown that its proper estimation and modeling…

This paper proposes a simple and robust zero-shot voice conversion system with a cycle structure and mel-spectrogram pre-processing. Previous works suffer from information loss and poor synthesis quality due to their reliance on a carefully…

Autoregressive music generation depends strongly on the audio tokenizer. Existing high-fidelity codecs often use residual multi-codebook quantization, which preserves reconstruction quality but complicates language modeling after sequence…

Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can…

Recent developments in neural speech synthesis and vocoding have sparked a renewed interest in voice conversion (VC). Beyond timbre transfer, achieving controllability on para-linguistic parameters such as pitch and Speed is critical in…

Suffering from limited singing voice corpus, existing singing voice synthesis (SVS) methods that build encoder-decoder neural networks to directly generate spectrogram could lead to out-of-tune issues during the inference phase. To…

The articulatory geometric configurations of the vocal tract and the acoustic properties of the resultant speech sound are considered to have a strong causal relationship. This paper aims at finding a joint latent representation between the…

In a hybrid speech model, both voiced and unvoiced components can coexist in a segment. Often, the voiced speech is regarded as the deterministic component, and the unvoiced speech and additive noise are the stochastic components.…

We present a novel high-fidelity real-time neural vocoder called VocGAN. A recently developed GAN-based vocoder, MelGAN, produces speech waveforms in real-time. However, it often produces a waveform that is insufficient in quality or…