Zewang Zhang

Zewang Zhang, Yibin Zheng, Xinhui Li et al.

In this paper, we develop a new multi-singer Chinese neural singing voice synthesis (SVS) system named WeSinger. To improve the accuracy and naturalness of synthesized singing voice, we design several specifical modules and techniques: 1) A deep bi-directional LSTM-based duration model with multi-scale rhythm loss and post-processing step; 2) A Transformer-alike acoustic model with progressive pitch-weighted decoder loss; 3) a 24 kHz pitch-aware LPCNet neural vocoder to produce high-quality singing waveforms; 4) A novel data augmentation method with multi-singer pre-training for stronger robustness and naturalness. To our knowledge, WeSinger is the first SVS system to adopt 24 kHz LPCNet and multi-singer pre-training simultaneously. Both quantitative and qualitative evaluation results demonstrate the effectiveness of WeSinger in terms of accuracy and naturalness, and WeSinger achieves state-of-the-art performance on the recent public Chinese singing corpus Opencpop\footnote{https://wenet.org.cn/opencpop/}. Some synthesized singing samples are available online\footnote{https://zzw922cn.github.io/wesinger/}.

Qiao Tian, Zewang Zhang, Chao Liu et al.

Attention based neural TTS is elegant speech synthesis pipeline and has shown a powerful ability to generate natural speech. However, it is still not robust enough to meet the stability requirements for industrial products. Besides, it suffers from slow inference speed owning to the autoregressive generation process. In this work, we propose FeatherTTS, a robust and efficient attention-based neural TTS system. Firstly, we propose a novel Gaussian attention which utilizes interpretability of Gaussian attention and the strict monotonic property in TTS. By this method, we replace the commonly used stop token prediction architecture with attentive stop prediction. Secondly, we apply block sparsity on the autoregressive decoder to speed up speech synthesis. The experimental results show that our proposed FeatherTTS not only nearly eliminates the problem of word skipping, repeating in particularly hard texts and keep the naturalness of generated speech, but also speeds up acoustic feature generation by 3.5 times over Tacotron. Overall, the proposed FeatherTTS can be $35$x faster than real-time on a single CPU.

Zewang Zhang, Qiao Tian, Heng Lu et al.

This paper investigates how to leverage a DurIAN-based average model to enable a new speaker to have both accurate pronunciation and fluent cross-lingual speaking with very limited monolingual data. A weakness of the recently proposed end-to-end text-to-speech (TTS) systems is that robust alignment is hard to achieve, which hinders it to scale well with very limited data. To cope with this issue, we introduce AdaDurIAN by training an improved DurIAN-based average model and leverage it to few-shot learning with the shared speaker-independent content encoder across different speakers. Several few-shot learning tasks in our experiments show AdaDurIAN can outperform the baseline end-to-end system by a large margin. Subjective evaluations also show that AdaDurIAN yields higher mean opinion score (MOS) of naturalness and more preferences of speaker similarity. In addition, we also apply AdaDurIAN to emotion transfer tasks and demonstrate its promising performance.

Qiao Tian, Zewang Zhang, Heng Lu et al.

In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recently proposed neural vocoder which utilized the linear predictive characteristic of speech signal in the WaveRNN architecture, can generate high quality speech with a speed faster than real-time on a single CPU core. However, LPCNet is still not efficient enough for online speech generation tasks. To address this issue, we adopt the multi-band linear predictive coding for WaveRNN vocoder. The multi-band method enables the model to generate several speech samples in parallel at one step. Therefore, it can significantly improve the efficiency of speech synthesis. The proposed model with 4 sub-bands needs less than 1.6 GFLOPS for speech generation. In our experiments, it can generate 24 kHz high-fidelity audio 9x faster than real-time on a single CPU, which is much faster than the LPCNet vocoder. Furthermore, our subjective listening test shows that the FeatherWave can generate speech with better quality than LPCNet.

Zewang Zhang, Zheng Sun, Jiaqi Liu et al.

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network. Especially, recurrent neural network and deep convolutional neural network have been applied in ASR successfully. Given the arising problem of training speed, we build a novel deep recurrent convolutional network for acoustic modeling and then apply deep residual learning to it. Our experiments show that it has not only faster convergence speed but better recognition accuracy over traditional deep convolutional recurrent network. In the experiments, we compare the convergence speed of our novel deep recurrent convolutional networks and traditional deep convolutional recurrent networks. With faster convergence speed, our novel deep recurrent convolutional networks can reach the comparable performance. We further show that applying deep residual learning can boost the convergence speed of our novel deep recurret convolutional networks. Finally, we evaluate all our experimental networks by phoneme error rate (PER) with our proposed bidirectional statistical n-gram language model. Our evaluation results show that our newly proposed deep recurrent convolutional network applied with deep residual learning can reach the best PER of 17.33\% with the fastest convergence speed on TIMIT database. The outstanding performance of our novel deep recurrent convolutional neural network with deep residual learning indicates that it can be potentially adopted in other sequential problems.

Zheng Sun, Jiaqi Liu, Zewang Zhang et al.

Creating aesthetically pleasing pieces of art, including music, has been a long-term goal for artificial intelligence research. Despite recent successes of long-short term memory (LSTM) recurrent neural networks (RNNs) in sequential learning, LSTM neural networks have not, by themselves, been able to generate natural-sounding music conforming to music theory. To transcend this inadequacy, we put forward a novel method for music composition that combines the LSTM with Grammars motivated by music theory. The main tenets of music theory are encoded as grammar argumented (GA) filters on the training data, such that the machine can be trained to generate music inheriting the naturalness of human-composed pieces from the original dataset while adhering to the rules of music theory. Unlike previous approaches, pitches and durations are encoded as one semantic entity, which we refer to as note-level encoding. This allows easy implementation of music theory grammars, as well as closer emulation of the thinking pattern of a musician. Although the GA rules are applied to the training data and never directly to the LSTM music generation, our machine still composes music that possess high incidences of diatonic scale notes, small pitch intervals and chords, in deference to music theory.