SDCLLGASNov 17, 2021

Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control

arXiv:2111.09146v12 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of generating expressive vocal performances for music production, but it is incremental as it builds on existing TTS methods with prosody control.

The paper tackles the problem of synthesizing rapping and singing voices from text using only read-only speech data, achieving high-quality output with increased naturalness as validated by subjective listening tests.

In this paper, a text-to-rapping/singing system is introduced, which can be adapted to any speaker's voice. It utilizes a Tacotron-based multispeaker acoustic model trained on read-only speech data and which provides prosody control at the phoneme level. Dataset augmentation and additional prosody manipulation based on traditional DSP algorithms are also investigated. The neural TTS model is fine-tuned to an unseen speaker's limited recordings, allowing rapping/singing synthesis with the target's speaker voice. The detailed pipeline of the system is described, which includes the extraction of the target pitch and duration values from an a capella song and their conversion into target speaker's valid range of notes before synthesis. An additional stage of prosodic manipulation of the output via WSOLA is also investigated for better matching the target duration values. The synthesized utterances can be mixed with an instrumental accompaniment track to produce a complete song. The proposed system is evaluated via subjective listening tests as well as in comparison to an available alternate system which also aims to produce synthetic singing voice from read-only training data. Results show that the proposed approach can produce high quality rapping/singing voice with increased naturalness.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes