High-fidelity singing voices usually require higher sampling rate (e.g., 48kHz, compared with 16kHz or 24kHz in speaking voices) with large range of frequency to convey expression and emotion. However, higher sampling rate causes the wider frequency band and longer waveform sequences and throws challenges for singing modeling in both frequency and time domains in singing voice synthesis (SVS). Conventional SVS systems that adopt moderate sampling rate (e.g., 16kHz or 24kHz) cannot well address the above challenges. In this paper, we develop HiFiSinger, an SVS system towards high-fidelity singing voice using 48kHz sampling rate. HiFiSinger consists of a FastSpeech based neural acoustic model and a Parallel WaveGAN based neural vocoder to ensure fast training and inference and also high voice quality. To tackle the difficulty of singing modeling caused by high sampling rate (wider frequency band and longer waveform), we introduce multi-scale adversarial training in both the acoustic model and vocoder to improve singing modeling. Specifically, 1) To handle the larger range of frequencies caused by higher sampling rate (e.g., 48kHz vs. 24kHz), we propose a novel sub-frequency GAN (SF-GAN) on mel-spectrogram generation, which splits the full 80-dimensional mel-frequency into multiple sub-bands (e.g. low, middle and high frequency bands) and models each sub-band with a separate discriminator. 2) To model longer waveform sequences caused by higher sampling rate, we propose a multi-length GAN (ML-GAN) for waveform generation to model different lengths of waveform sequences with separate discriminators. 3) We also introduce several additional designs and findings in HiFiSinger that are crucial for high-fidelity voices, such as adding F0 (pitch) and V/UV (voiced/unvoiced flag) as acoustic features, choosing an appropriate window/hop size for mel-spectrogram, and increasing the receptive field in vocoder for long vowel modeling in singing voices. Experiment results show that HiFiSinger synthesizes high-fidelity singing voices with much higher quality: 0.32/0.44 MOS gain over 48kHz/24kHz baseline and 0.83 MOS gain over previous SVS systems. Audio samples are available at https://speechresearch.github.io/hifisinger/.

This paper presents XiaoiceSing, a high-quality singing voice synthesis system which employs an integrated network for spectrum, F0 and duration modeling. We follow the main architecture of FastSpeech while proposing some singing-specific design: 1) Besides phoneme ID and position encoding, features from musical score (e.g.note pitch and length) are also added. 2) To attenuate off-key issues, we add a residual connection in F0 prediction. 3) In addition to the duration loss of each phoneme, the duration of all the phonemes in a musical note is accumulated to calculate the syllable duration loss for rhythm enhancement. Experiment results show that XiaoiceSing outperforms the baseline system of convolutional neural networks by 1.44 MOS on sound quality, 1.18 on pronunciation accuracy and 1.38 on naturalness respectively. In two A/B tests, the proposed F0 and duration modeling methods achieve 97.3% and 84.3% preference rate over baseline respectively, which demonstrates the overwhelming advantages of XiaoiceSing.

In this paper 1 , we develop DeepSinger, a multilingual multi-singer singing voice synthesis (SVS) system, which is built from scratch using singing training data mined from music websites. The pipeline of DeepSinger consists of several steps, including data crawling, singing and accompaniment separation, lyrics-to-singing alignment, data filtration, and singing modeling. Specifically, we design a lyrics-to-singing alignment model to automatically extract the duration of each phoneme in lyrics starting from coarse-grained sentence level to fine-grained phoneme level, and further design a multilingual multi-singer singing model based on a feed-forward Transformer to directly generate linear-spectrograms from lyrics, and synthesize voices using Griffin-Lim. DeepSinger has several advantages over previous SVS systems: 1) to the best of our knowledge, it is the first SVS system that directly mines training data from music websites, 2) the lyrics-to-singing alignment model further avoids any human efforts for alignment labeling and greatly reduces labeling cost, 3) the singing model based on a feed-forward Transformer is simple and efficient, by removing the complicated acoustic feature modeling in parametric synthesis and leveraging a reference encoder to capture the timbre of a singer from noisy singing data, and 4) it can synthesize singing voices in multiple languages and multiple singers. We evaluate DeepSinger on our mined singing dataset that consists of about 92 hours data from 89 singers on three languages (Chinese, Cantonese and English). The results demonstrate that with the singing data purely mined from the Web, DeepSinger can synthesize high-quality singing voices in terms of both pitch accuracy and voice naturalness 2. CCS CONCEPTS • Computing methodologies → Natural language processing; • Applied computing → Sound and music computing.

No abstract

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.

Detecting singing-voice in polyphonic instrumental music is critical to music information retrieval. To train a robust vocal detector, a large dataset marked with vocal or non-vocal label at frame-level is essential. However, frame-level labeling is time-consuming and labor expensive, resulting there is little well-labeled dataset available for singing-voice detection (S-VD). Hence, we propose a data augmentation method for S-VD by transfer learning. In this study, clean speech clips with voice activity endpoints and separate instrumental music clips are artificially added together to simulate polyphonic vocals to train a vocal /non-vocal detector. Due to the different articulation and phonation between speaking and singing, the vocal detector trained with the artificial dataset does not match well with the polyphonic music which is singing vocals together with the instrumental accompaniments. To reduce this mismatch, transfer learning is used to transfer the knowledge learned from the artificial speech-plus-music training set to a small but matched polyphonic dataset, i.e., singing vocals with accompaniments. By transferring the related knowledge to make up for the lack of well-labeled training data in S-VD, the proposed data augmentation method by transfer learning can improve S-VD performance with an F-score improvement from 89.5% to 93.2%.

No abstract

Pitch extraction, also known as fundamental frequency estimation, is a long-term task in audio signal processing. Especially, due to the presence of accompaniment, vocal pitch extraction in polyphonic music is more challenging. So far, most of deep learning approaches use log mel spectrogram as input, which neglect the phase information. In addition, shallow networks have been applied on waveform directly, which may not handle contaminated vocal data well. In this paper, a deep convolutional residual network is proposed. It analyzes and extracts effective feature from waveform automatically. Residual learning can reduce model degradation due to the skip connection and residual mapping. In comparison to reported results, the proposed approach shows 5% and 4% improvement on overall accuracy(OA) and raw pitch accuracy(RPA) respectively.