Voice engine

Abstract: The current paper investigates an essential design component of virtual humans, the voice they communicate with, by examining the impact of varied voice types. A standard voice effect has held that human voices should be paired with virtual humans. The current study revisits this effect. In a randomized trial, virtual humans used one of three voice types (classic and modern text-to-speech engines, as well as human voice) to present information to a sample of participants from an online population. The impact of each voice type on learning, cognitive load, and perceptions of the virtual human were examined. The study found that the modern voice engine produced significantly more learning on transfer outcomes, had greater training efficiency, and was rated at the same level as an agent with a human voice for facilitating learning and credibility while outperforming the older speech engine. These results call into question previous results using older voice engines and the claims of the voice effect.

Abstract: An intelligent client agent and a method for using the client agent to operate a hybrid online/offline client application. A mobile client device is configured with a client agent comprising a dispatcher for receiving and responding to page requests from a client browser, a cache for storing the presentation formats of pages, a database for storing data for the pages, a voice engine for interaction with the application user in audio, and a script engine for assembling a page to be presented graphically or aurally. Instead of storing each page (e.g., of an application) as a static composition, the presentation format of the page is stored separate from content (e.g., data). At the time of assembly, the desired content is retrieved and bound to the presentation format and provided to the user.

Abstract: The invention discloses a voice recognition method, voice recognition equipment and electronic equipment. The method comprises the steps: firstly, a corresponding voice correction instruction is output to a voice engine by detecting a sample environment corresponding to voice and judging together with the previous environment type; then the voice to be recognized is input to the voice engine and a noise type detection engine at the same time; the voice engine utilizes the voice correction instruction to correct the voice to be recognized; the quality of original voice cannot be damaged due to the processing of noises; a corresponding original recognition result is output; the noise type detection engine utilizes the voice to be recognized and voice training samples under different environments to judge the current environment type; finally, the confidence coefficient in the original recognition result is adjusted by using the current environment type, so that the recognition effect of the finally output voice recognition result is enabled to provide excellent user experience for a user under the current environment.

Abstract: The invention discloses an intelligent voice test system and method for a terminal. The system comprises the terminal to be tested, a test computer and an intelligent voice engine or model, wherein the intelligent voice engine or model is arranged on a cloud or the local terminal to be tested, the test computer is connected with the terminal to be tested, and the terminal to be tested is connected with the intelligent voice engine or model on the cloud in a wireless mode. The method includes the following steps that the terminal to be tested is connected with the cloud in a wireless mode to be identified under the situation that the intelligent voice engine or model is located on the cloud, the terminal to be tested is directly and locally identified under the situation that the intelligent voice engine or model is arranged locally, and under the two situations, the test computer can directly obtain identification results from the terminal to be tested and conduct performance analysis. Compared with the prior art, the terminal intelligent voice test system and method can be used for testing intelligent voice performance of the terminal to be tested and the cloud and are comprehensive and accurate in testing, simple, flexible and easy to use.