Baidu. has been granted a patent for a voice generating method that involves processing text to determine associated context and prosodic features. The method generates a target voice by analyzing spectrum features derived from these associations, enhancing the quality and relevance of the generated speech. GlobalData’s report on Baidu gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Baidu, Behavioral analytics was a key innovation area identified from patents. Baidu's grant share as of July 2024 was 50%. Grant share is based on the ratio of number of grants to total number of patents.
Voice generation method using text and prosodic features
The granted patent US12073822B2 outlines a voice generating method that involves several steps to process text and generate corresponding voice output. The method begins with acquiring a text to be processed and determining its associated context text. This context text is then used to acquire associated prosodic features and text features, which include semantic information. The method further involves determining a spectrum feature based on the acquired prosodic and text features, ultimately leading to the generation of a target voice that corresponds to the original text. The claims detail a systematic approach to processing the text, including the prediction of various features such as word, voice, and prosodic features, which are essential for creating a natural-sounding voice output.
Additionally, the patent describes the use of electronic devices equipped with processors and memory to execute the voice generating method. The device is designed to perform the same steps as outlined in the method claims, ensuring that the text is processed effectively to produce the desired voice output. The claims also emphasize the importance of splicing features and predicting context-related features to enhance the accuracy and quality of the generated voice. This comprehensive approach aims to improve the naturalness and expressiveness of synthesized speech, making it more suitable for various applications in voice technology.
To know more about GlobalData’s detailed insights on Baidu, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
