Abstract
Speech synthesis, also known as text-to-speech (TTS), has attracted increasingly more attention. Recent advances on speech synthesis are overwhelmingly contributed by deep learning or even end-to-end techniques which have been utilized to enhance a wide range of application scenarios such as intelligent speech interaction, chatbot or conversational artificial intelligence (AI). For speech synthesis, deep learning based techniques can leverage a large scale of <text, speech> pairs to learn effective feature representations to bridge the gap between text and speech, thus better characterizing the properties of events. To better understand the research dynamics in the speech synthesis field, this paper firstly introduces the traditional speech synthesis methods and highlights the importance of the acoustic modeling from the composition of the statistical parametric speech synthesis (SPSS) system. It then gives an overview of the advances on deep learning based speech synthesis, including the end-to-end approaches which have achieved start-of-the-art performance in recent years. Finally, it discusses the problems of the deep learning methods for speech synthesis, and also points out some appealing research directions that can bring the speech synthesis research into a new frontier.
Highlights
IntroductionKnown as text-to-speech (TTS), is a comprehensive technology that involves many disciplines such as acoustics, linguistics, digital signal processing and statistics
Speech synthesis, known as text-to-speech (TTS), is a comprehensive technology that involves many disciplines such as acoustics, linguistics, digital signal processing and statistics.The main task is to convert text input into speech output
The Deep learning (DL)-based speech synthesis models adopt complete context information and distributed representation to replace the clustering process of the context decision tree in hidden Markov models (HMMs), and use multiple hidden layers to map the context features to high-dimensional acoustic features, making the quality of the synthesized speech better than the traditional methods
Summary
Known as text-to-speech (TTS), is a comprehensive technology that involves many disciplines such as acoustics, linguistics, digital signal processing and statistics. The main task is to convert text input into speech output. With the development of speech synthesis technologies, from the previous formant based parametric synthesis [1,2], waveform concatenation based methods [3,4,5] to the current statistical parametric speech synthesis (SPSS) [6], the intelligibility and naturalness of the synthesized speech have been improved greatly. The main reason is that the existing methods are based on shallow models that contain only one-layer nonlinear transformation units, such as hidden Markov models (HMMs) [7,8] and maximum Entropy (MaxEnt) [9].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
