Related papers: UnivNet: A Neural Vocoder with Multi-Resolution Sp…
We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis. We also examine choice of neural vocoder for waveform synthesis, as well as…
Recently, deep learning-based generative models have been introduced to generate singing voices. One approach is to predict the parametric vocoder features consisting of explicit speech parameters. This approach has the advantage that the…
Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end…
Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, we propose SpecGrad that adapts the diffusion noise so that…
In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for…
Recently, GAN-based neural vocoders such as Parallel WaveGAN, MelGAN, HiFiGAN, and UnivNet have become popular due to their lightweight and parallel structure, resulting in a real-time synthesized waveform with high fidelity, even on a CPU.…
This paper addresses the challenge of enhancing the realism of vocoder-generated singing voice audio by mitigating the distinguishable disparities between synthetic and real-life recordings, particularly in high-frequency spectrogram…
Universal speech enhancement (USE) aims to restore speech signals from diverse distortions across multiple sampling rates. We propose UniPASE, an extension of the low-hallucination PASE framework tailored for USE. At its core is…
For articulatory-to-acoustic mapping using deep neural networks, typically spectral and excitation parameters of vocoders have been used as the training targets. However, vocoding often results in buzzy and muffled final speech quality.…
In text-to-speech (TTS) and voice conversion (VC), acoustic features, such as mel spectrograms, are typically used as synthesis or conversion targets owing to their compactness and ease of learning. However, because the ultimate goal is to…
To investigate the processing of speech in the brain, simple linear models are commonly used to establish a relationship between brain signals and speech features. However, these linear models are ill-equipped to model a highly dynamic and…
Separating vocal elements from musical tracks is a longstanding challenge in audio signal processing. This study tackles the distinct separation of vocal components from musical spectrograms. We employ the Short Time Fourier Transform…
Singing Voice Separation (SVS) tries to separate singing voice from a given mixed musical signal. Recently, many U-Net-based models have been proposed for the SVS task, but there were no existing works that evaluate and compare various…
We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-learning advances to provide a highly realistic signal…
Neural vocoders are central to speech synthesis; despite their success, most still suffer from limited prosody modeling and inaccurate phase reconstruction. We propose a vocoder that introduces prosody-guided harmonic attention to enhance…
For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking…
This paper explores the potential universality of neural vocoders. We train a WaveRNN-based vocoder on 74 speakers coming from 17 languages. This vocoder is shown to be capable of generating speech of consistently good quality (98% relative…
In speaker verification systems, the utilization of short utterances presents a persistent challenge, leading to performance degradation primarily due to insufficient phonetic information to characterize the speakers. To overcome this…
Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous speakers across…
Pattern recognition from audio signals is an active research topic encompassing audio tagging, acoustic scene classification, music classification, and other areas. Spectrogram and mel-frequency cepstral coefficients (MFCC) are among the…