New method for high-speed synthesis of natural voices

February 6, 2019, Research Organization of Information and Systems

A research team at the National Institute of Informatics (NII/Tokyo, Japan) including Xin Wang, Shinji Takaki and Junichi Yamagishi has developed a neural source-filter (NSF) model for high-speed, high-quality voice synthesis. This technique, which combines recent deep-learning algorithms and a classical speech production model dated back to the 1960s, is capable not only of generating high-quality voice waveforms closely resembling the human voice, but also of conducting stable learning via neural networks.

To date, many speech synthesis systems have adopted the vocoder approach, a method for synthesizing speech waveforms that is widely used in cellular-phone networks and other applications. However, the quality of the speech waveforms synthesized by these methods has remained inferior to that of the human voice. In 2016, an influential overseas technology company proposed WaveNet—a speech-synthesis method based on deep-learning algorithms—and demonstrated the ability to synthesize high-quality speech waveforms resembling the human voice. However, one drawback of WaveNet is the extremely complex structure of its neural networks, which demand large quantities of voice data for and require parameter tuning and various other laborious trial-and-error procedures to be repeated many times before accurate predictions can be obtained.

Overview and achievements of the research

One of the most well-known vocoders is the source-filter vocoder, which was developed in the 1960s and remains in widespread use today. The NII research team infused the conventional source-filter vocoder method with modern neural-network algorithms to develop a new technique for synthesizing high-quality speech waveforms resembling the human voice. Among the advantages of this neural source-filter (NSF) method is the simple structure of its , which require only about one hour of data for machine learning and can obtain correct predictive results without extensive parameter tuning. Moreover, large-scale listening tests have demonstrated that speech waveforms produced by NSF techniques are comparable in quality to those generated by WaveNet.

Because the theoretical basis of NSF differs from the patented technologies used by influential overseas ICT companies, the adoption of NSF techniques is likely to spur new technological advances in synthesis. For this reason, the source code implementing the NSF has been made available to the public at no cost, allowing it to be widely used.

Explore further: WaveGlow: A flow-based generative network to synthesize speech

More information: Neural source-filter-based waveform model for statistical parametric speech synthesis.

Source code: … ject-CURRENNT-public

Trained models (may be executed to generate English-language voices): … ect-CURRENNT-scripts

Voice samples (Japanese or English):

Related Stories

WaveGlow: A flow-based generative network to synthesize speech

November 19, 2018

A team of researchers at NVIDIA has recently developed WaveGlow, a flow-based network that can generate high-quality speech from melspectrograms, which are acoustic time-frequency representations of sound. Their method, outlined ...

Engineers translate brain signals directly into speech

January 29, 2019

In a scientific first, Columbia neuroengineers have created a system that translates thought into intelligible, recognizable speech. By monitoring someone's brain activity, the technology can reconstruct the words a person ...

Scientists improve deep learning method for neural networks

August 17, 2018

Researchers from the Institute of Cyber Intelligence Systems at the National Research Nuclear University MEPhI (Russia) have recently developed a new learning model for the restricted Boltzmann machine (a neural network), ...

Recommended for you


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.