Microsoft Technology Licensing, LLC

Other

Chiwei Che

Sheng-Yao Shih

Chih-Chung Wang

Yun-Chiang Kung

Matthew Robert Scott

Sheng Zhao

Jingyang Xu

Hao Wei

Weipeng Liu

Xi Chen

Huihua Hou

Byron Huntley Changuion

Weijiang Xu

XiXi Chen

Byron Changuion

Jacky Chen

Zhi Hong Li

Fileno A Alleva

Fang Zhang

Xin Gong

Binggong Ding

Mingyan Xie

Jian-Chao Wang

Lu-Jun Yuan

Mingyang Xie

Shenghao Qin

Example apparatus and methods concern improved input of radicals. Example apparatus and methods facilitate more efficiently inputting Chinese radicals using a touch screen. One example method includes displaying a labeled soft key on a touch screen device. The label may represent all or a portion of a radical. The example method includes accepting a touch input associated with the soft key and then taking an action based on the label and the touch input. The action may include inputting a radical or updating the display on the touch screen. Updating the display may facilitate iterative and intuitive progress through radical construction leading to radical selection and input.

Inputting radical on touch screen device

Non-limiting examples described herein relate to processing for transcoding textual content into audio signals. In some examples, transcoding services are provided over a distributed network, for example, through an interaction between a client device and a server device. For instance, a client device may transmit a selection of a document to a server device. The server device may access a document source for the document and transcode content from the document source into speech. The server device may transmit the transcoded content to the client device, for example, where the client device may output the transcoded content. For instance, the transcoded content may be an audio file that is streamed by the client device.

Audio output of a document from mobile device

An input method editor (IME) described herein couples scenarios of the input of the user with specific network services to offer more relevant and richer candidates for higher input productivity. Data relating to a computer application in which the input candidates are to be input and/or context relating to a user-submitted query is collected and analyzed to determine a scenario. The input candidates may include text candidates and rich candidates. The IME may select a scenario-tuned and type specific engine to identify the text candidates and/or rich candidates. The scenario-tuned text candidate engines leverage scenario-tuned language models and lexicons, and the scenario-tuned rich candidate engines leverage scenario-relevant web services, such as image, mapping, and video search, when available and appropriate.

Scenario-adaptive input method editor

Architecture for playing a document converted into an audio format to a user of an audio-output capable device. The user can interact with the device to control play of the audio document such as pause, rewind, forward, etc. In more robust implementation, the audio-output capable device is a mobile device (e.g., cell phone) having a microphone for processing voice input. Voice commands can then be input to control play ('reading') of the document audio file to pause, rewind, read paragraph, read next chapter, fast forward, etc. A communications server (e.g., email, attachments to email, etc.) transcodes text-based document content into an audio format by leveraging a text-to-speech (TTS) engine. The transcoded audio files are then transferred to mobile devices through viable transmission channels. Users can then play the audio-formatted document while freeing hand and eye usage for other tasks.

Methods, systems, and computer-storage media having computer-usable instructions embodied thereon, for displaying and inputting symbols are provided. Bopomofo symbols are phonetic representations of Chinese characters. To accommodate all the Bopomofo symbols on a mobile device keyboard without sacrificing key size, the Bopomofo keys are dynamically disabled based on grammar rules and user inputs. For example, a symbol that is not eligible to follow an input symbol is disabled such that it does not distract a user searching for a symbol in the keyboard. Further, specific keys on a keyboard are dynamically replaced with tone keys once a user inputs a symbol. A user interface for displaying the symbols is, thus, consistent and easy to navigate for a user.

Displaying and inputting symbols

An interactive prompt generation and TTS optimization tool with a user-friendly graphical user interface is provided. The tool accepts HTS abstraction or speech recognition processed input from a user to generate an enhanced initial waveform for synthesis. Acoustic features of the waveform are presented to the user with graphical visualizations enabling the user to modify various parameters of the speech synthesis process and listen to modified versions until an acceptable end product is reached.

Interactive TTS optimization tool

Techniques to create and share custom voice fonts are described. An apparatus may include a preprocessing component to receive voice audio data and a corresponding text script from a client and to process the voice audio data to produce prosody labels and a rich script. The apparatus may further include a verification component to automatically verify the voice audio data and the text script. The apparatus may further include a training component to train a custom voice font from the verified voice audio data and rich script and to generate custom voice font data usable by the TTS component. Other embodiments are described and claimed.

Techniques to create a custom voice font

Growing community of inventors

Beijing, China

Chiwei Che