Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling

Yi, Yuan-Hao; Ai, Yang; Ling, Zhen-Hua; Dai, Li-Rong

doi:10.48550/arxiv.1906.08977

Cited by 10 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4) Recent Progress on Neural Vocoders: More recently, speaker independent WaveRNN-based neural vocoder [63] became popular as it can generate human-like voices from both in-domain and out-of-domain spectrogram [99]- [101]. Another well-known neural vocoder that achieves highquality synthesis performance is WaveGlow [64].…”

Section: A Speech Analysis and Reconstructionmentioning

confidence: 99%

An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning

Şişman

Yamagishi

King

et al. 2020

Preprint

View full text Add to dashboard Cite

Speaker identity is one of the important characteristics of human speech. In voice conversion, we change the speaker identity from one to another, while keeping the linguistic content unchanged. Voice conversion involves multiple speech processing techniques, such as speech analysis, spectral conversion, prosody conversion, speaker characterization, and vocoding. With the recent advances in theory and practice, we are now able to produce human-like voice quality with high speaker similarity. In this paper, we provide a comprehensive overview of the state-of-the-art of voice conversion techniques and their performance evaluation methods from the statistical approaches to deep learning, and discuss their promise and limitations. We will also report the recent Voice Conversion Challenges (VCC), the performance of the current state of technology, and provide a summary of the available resources for voice conversion research.

show abstract

Section: A Speech Analysis and Reconstructionmentioning

confidence: 99%

An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning

Şişman

Yamagishi

King

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Rooted in [17], many subsequent works for expressive singing voice synthesis focus on improvement about these control parameters, especially melody, dynamics a.k.a pitch and energy. For example, to predict pitch feature better, Yi et al [18] utilized deep autoregressive network to capture the dependencies among the consecutive acoustic features. Zhuang et al [1] separated the pitch feature from the acoustic feature to avoid the interdependence between these pitch features and the timbre features.…”

Section: Introductionmentioning

confidence: 99%

Singing Voice Synthesis with Vibrato Modeling and Latent Energy Representation

Song

Zhang

et al. 2022

2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)

View full text Add to dashboard Cite

This paper proposes an expressive singing voice synthesis system by introducing explicit vibrato modeling and latent energy representation. Vibrato is essential to the naturalness of synthesized sound, due to the inherent characteristics of human singing. Hence, a deep learning-based vibrato model is introduced in this paper to control the vibrato's likeliness, rate, depth and phase in singing, where the vibrato likeliness represents the existence probability of vibrato and it would help improve the singing voice's naturalness. Actually, there is no annotated label about vibrato likeliness in existing singing corpus. We adopt a novel vibrato likeliness labeling method to label the vibrato likeliness automatically. Meanwhile, the power spectrogram of audio contains rich information that can improve the expressiveness of singing. An autoencoder-based latent energy bottleneck feature is proposed for expressive singing voice synthesis. Experimental results on the open dataset NUS48E show that both the vibrato modeling and the latent energy representation could significantly improve the expressiveness of singing voice. The audio samples are shown in the demo website 1 .

show abstract

“…Recent years, many deep learning based methods have been introduced into SVS to generate high quality singing voices, such DNN [1] and LSTM [2]. In addition, autoregressive models, like Tacotron2 [3] have been successfully applied to SVS task [4,5,6].…”

Section: Introductionmentioning

confidence: 99%

Adversarially Trained Multi-Singer Sequence-to-Sequence Singing Synthesizer

Wu¹,

Luan²

2020

Interspeech 2020

View full text Add to dashboard Cite

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 multisinger framework to leverage all the existing singing data of different singers. To attenuate the issue of musical score unbalance among singers, we incorporate an adversarial task of singer classification to make encoder output less singer dependent. Furthermore, we apply multiple random window discriminators (MRWDs) on the generated acoustic features to make the network be a GAN. Both objective and subjective evaluations indicate that the proposed synthesizer can generate higher quality singing voice than baseline (4.12 vs 3.53 in MOS). Especially, the articulation of high-pitched vowels is significantly enhanced.

show abstract

Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling

Cited by 10 publications

References 10 publications

An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning

An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning

Singing Voice Synthesis with Vibrato Modeling and Latent Energy Representation

Adversarially Trained Multi-Singer Sequence-to-Sequence Singing Synthesizer

Contact Info

Product

Resources

About