In recent years, with the popularity of deep learning, speech synthesis technology has developed rapidly and achieved many good achievements. Among them, the technology of speech synthesis for personalized voiceprint features has also become a research focus. In the existing work, the model for personalized voiceprint feature speech synthesis based on GANs has achieved certain results. The model successfully synthesized speech with personalized voiceprint features in a non-autoregressive way, but the audio quality of the synthesized speech and efficiency was low, and the model training time was long. In this paper, we improve the model through techniques such as multi-domain signal processing. Specifically, we reduce a lot of training time by optimizing several parameters of the model. In addition, the architecture of the model has been improved to a certain extent, which effectively improves the MOS score of synthesized speech.
With the development of natural language processing technology and artificial intelligence technology, more and more industrial applications have landed. Our lives have also been improved through intelligent voice assistants. In life, we can control various home appliances by talking to the voice assistant, and we can also chat with the AI voice assistant. In the final analysis, these activities are actually the expansion of the dialogue system, and in the dialogue system, historical dialogue information plays a vital role. The contribution of this article is to use the cosine similarity to compare the current question with the chat information that occurred before. If the similarity is high, it is added to the sentence embedding of the final model input. The advantage of this is that it improves the accuracy of the machine in answering questions in multiple rounds of conversations.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.