ViviVoice provides the most abundant sound library, and expands according to customer needs, adapts to the needs of diverse voice application business; can automatically and accurately perform intelligent text analysis and pre-processing; the synthesized voice is clear, smooth and natural, so that users get the most Good performance experience; powerful parameter setting and adjustment capabilities, easy to adjust various flexible voice effects,
False can be really chaotic masters Keda News fly vivivoice software evaluation. As the new power engine for personalized voice services, ViviVoice will add a unique charm to a wide range of voice applications.
Rich tone dominates the trend of personalized voice services
ViviVoice leads the new trend of personalized voice services, using industry-leading trainable speech synthesis technology, which can quickly provide a wide range of languages ​​and diverse sound selections for voice applications, and adhere to the highest quality performance consistent with HKUST's voice technology. Users provide a personalized voice service experience.
In the ViviVoice product, the following sound banks are available:
No. Name Voice Language 1Xiao Yan Xiaoyan Young Female Voice Mandarin 2Xiao Feng Xiaofeng Young Male Mandarin 3Xiao Qin Xiaoqin Youth Female Mandarin 4Xiao Jia Xiaojia Junior Female Mandarin 5Xiao Chang Xiaochang Young Female Mandarin 6Nan Nan Nan Nan Children's Female Mandarin 7Lao Sun Old Sun Senior Male voice Mandarin 8Xiao Rong Xiaorong young female voice Sichuan dialect 9Xiao Yun Xiaoyan young female voice Northeast dialect 10XiaoYing Xiaoying young female voice Shaanxi dialect 11Xiao Qiang Xiaoqiang young male voice Hunan dialect 12Xiao Kun Xiaokun young male Henan dialect 13Xiao Li Xiaoli young female Taiwanese Mandarin 14Xiao Mei Xiaomei young female voice Cantonese 15Terry young female voice pure English
Because ViviVoice uses the most advanced Chinese text, prosody analysis algorithm and training-based parameter synthesis method, the synthesis effect can reach the level of real people reading, and the period of constructing a high-quality sound library can be greatly shortened compared with the past, which makes the University of Science and Technology Xunfei is able to respond more quickly to the new demands of personalized voice applications and continue to provide more and better sound banks. For a list of the latest sound libraries currently supported by ViviVoice, please visit the HKUST website.
ViviVoice provides a rich and natural sound library. In practical applications, it can flexibly switch real-time sound banks according to business needs.
Highly expressive synthesis engine
ViviVoice speech synthesis software supports both doubt and exclamation, supports happy and sad emotions, fully reflects the product's personalization and entertainment features, and gives you different listening experiences.
Highly accurate intelligent text analysis and preprocessing
ViviVoice speech synthesis software has high-accuracy intelligent text analysis and pre-processing technology to ensure the final synthesized speech is accurate, clear and smooth. Thanks to the deep accumulation of UC in the research and practice of linguistics, through close cooperation with relevant authoritative scientific research institutions such as the Institute of Languages ​​of the Chinese Academy of Social Sciences, and a vast pool of professional knowledge bases accumulated based on a broad application practice platform, Training and optimization, even in the face of difficulties in language analysis processing, such as polyphonic words, special symbols, prosodic phrases, unregistered words (such as place names, names), etc., can guarantee a highly accurate automatic processing results.
Smooth effect and powerful sound adjustment
Using the method of parameter synthesis, ViviVoice products can control the parameters affecting the synthesis effect very conveniently, which can better eliminate the inconsistency such as the frustration of traditional voice stitching methods, and the synthesized speech is more smooth and natural. In response to the general needs of the mainstream application environment, the University of Science and Technology has collected a wide range of corpus for practical applications, and optimized digital values ​​and phrase phrases with specific models to make the synthesis more clear, accurate, full, and more rhythmic. On the premise of ensuring high-quality speech synthesis, it can adjust many parameters such as volume, pitch, speech rate, etc., with rich characteristic sound effects, making the voice service more lively and full of fun.
Comprehensive and complete functional features
Reasonable architecture to meet high stability application requirements
ViviVoice adopts TCP/IP-based efficient network speech synthesis service and centralized resource management mechanism to form a client-resource manager-server organic combination architecture to build a flexible and scalable solution. The architecture, its high availability has been tested by large-scale, critical business applications in a number of key industries, ensuring reliable 7&TImes; 24-hour automated voice services.
Rich parameter setting and adjustment functions to adapt to various complex application environments
ViviVoice products provide a comprehensive set of parameters and adjustments and tools to help users flexibly and efficiently control and manage speech synthesis. Provides tools for global parameters (such as volume, speech rate, pitch, etc.), user dictionaries, user rules, and custom resource bundles to be configured and managed in a unified manner; digital, punctuation, English pronunciation mode settings; Chinese and English additions, You can specify pinyin or phonetic symbols for each word, etc.; provide a unified and easy-to-use graphical user interface for operation settings, and can be dynamically set and adjusted through API parameters, and also support CSSML (Chinese Speech Synthesis Markup Language) Mark, describe and control.
Flexible and efficient development interface to accelerate integration and application publishing
ViviVoice DK provides various development interfaces for different development tools, different integration requirements and solutions, including: standard development interface (dynamic link library DLL), Quick TTS interface, COM component, Microsoft SAPI development interface and Java development interface, new The pre-recorded background sound development interface has been added, and developers can flexibly choose according to actual needs. Extensive development routines and documentation are provided to help accelerate the voice application development process.
Efficient and convenient enhancement toolset
In the process of support for long-term integrated development and application practice, HKUST has summarized the ways in which customers use speech synthesis and the characteristics of their applications, and gradually developed a series of tools that make it easy for users to use speech synthesis functions in different environments. ViviVoice's enhanced toolset suite includes a variety of easy-to-use and efficient components such as offline voice application tools, CSSML visual editing tools, DOC/XLS text format conversion tools and more. By using these tools, users can simplify development, optimize synthesis, and facilitate system maintenance and technical support.
Comprehensive character set, voice data format support
Full support for GB2312, GBK, BIG5, GB18030, UTF-8 and UNICODE coded character sets, automatic recognition of UNICODE text; support for direct output of multiple sample rate speech data formats (including 6K/8K/11K/16K) linear Wav, A /U rates voice data in a variety of formats such as Wav and Vox.
Desktop application level system size
The high-quality voice synthesis effect, combined with the ultra-small system size, reduces resource consumption, further reduces special requirements and desktop application thresholds, and is more in line with the needs of various voice application services.
Platform support
The speech synthesis software of Keda Xunfei has the most comprehensive platform support. Nearly all major interactive voice response (IVR) platforms support the voice synthesis products of HKUST. For further information, please contact your IVR provider or HKUST. ViViVoice supports mainstream operating systems. It is easy to find successful implementation cases for customers in various application environments.
Careful and thoughtful optimization
Optimize customized, efficient application solutions
Provides an efficient solution that optimizes the performance of the mainstream application environment represented by the custom resource package (loaded on the synthesis engine to effectively improve the voice effect of the established application domain) and the mainstream application environment represented by CSSML and virtual indefinite length tools, significantly improving the actual application effect. . HKUST's professional service system provides efficient customization and optimization solutions to enhance the customer experience and help customers achieve the continued success of voice self-service.
CSSML, the effect is more comfortable
CSSML (Chinese Speech Synthesis Markup Language) is a Chinese speech data description specification proposed and led by Keda Xunfei. The standard has received great attention and support from the National 863 Expert Group, the National Beacon Committee and the State Bureau of Technical Supervision. In 2005, it officially passed the review of the National Standardization Organization and became an important part of the Chinese speech synthesis technology standards and norms. Designed and expanded for Chinese speech applications, CSSML provides flexible annotation and control of a wide range of features and is compatible with open standard SSML.
Pre-recorded voice, smooth and easy to use
ViviVoice adopts the pre-recorded unified management function pioneered by the University of Science and Technology. It uses pre-recording as a resource of the speech synthesis system, and makes the pre-recording and synthesizing sounds easier to match and smoother through the intelligent matching of the prompt sound and the composite template. At the same time, it avoids frequent switching of transition and transition of prompt sound playback and speech synthesis, simplifies the complexity of the application process, and further improves the service effect and quality.
Background music, quick upgrade user checkup
ViviVoice adopts the background sound function pioneered by the University of Science and Technology. Through the simple and easy-to-use tools provided by the system, it can add background music conveniently and efficiently, adjust the volume contrast of background music and synthesized speech, and directly audit the actual effect to make voice service. More intimate and natural.
Featured sound effects to create more entertainment colors
ViviVoice adopts the unique sound function pioneered by the industry's first in the industry. The system can add distinctive sound effects such as pick-up, reverb, and metal sound while synthesizing voice. It is very suitable for making some sci-fi, entertainment and funny sounds. The effect can bring a new experience to the user.
We offer rechargeable li ion and Lipo Battery cells from industry's leading manufacturers, Panasonic cells, Sanyo cells, Moli cell, ATL cells, BAK cells, DLG cells, HYB cells, Samsung cells, LG cells, Maxell Cells. With contacts inside big manufacturers, we are able to supply authentic cells in wide variations of sizes, capacities, and power performances to meet your needs. In addtion we provide processing service to add proteced PCB in cell, to put heat shrink tubes, wires with designated connector, or to design unique plastic case with coaxial DC port.
Rechargeable Batteries,Rechargeable Lithium Batteries,Rechargeable Cell,Lithium Ion Rechargeable Batteries
Asarke Industry Co., Limited , https://www.asarke-industry.com