Bo Yan

20040203096, Oct 14, 2004

May 14, 2004

10/474163

Nina Raben - Rockville MD, US
Nina Lu - Rockville MD, US
Bo Yan - Rockville MD, US
Paul Plotz - Washington DC, US
Yesenia Rivera - Bethesda MD, US

C12N009/36
C07H021/04

435/069100, 435/320100, 435/325000, 435/206000, 536/023200

The invention provides recombinant native lysosomal enzymes produced by liver cells, preferably in vitro, and methods of using the native recombinant lysosomal enzymes to treat enzyme deficiencies in vivo. Lysosomal enzymes, including acid alpha-glucosidase (GAA), produced by liver cells apparently undergo the post-translational modifications necessary to achieve good enzymatic activity. The resulting enzymes can be taken up by various other cells and can correct phenotypic abnormalities of distant organs with enzyme deficiencies. In certain preferred embodiments, the enzyme is GAA and the methods are especially adapted for treatment of type II glycogen storage disease in mammals, including humans.

20220310058, Sep 29, 2022

Nov 3, 2020

17/280008

- , US
Li JIANG - Kirkland WA, US
Xuedong HUANG - Bellevue WA, US
Lijuan QIN - Redmond WA, US
Lei HE - Beijing, CN
Binggong DING - Beijing, CN
Bo YAN - Sammamish WA, US
Chunling MA - Beijing, CN
Raunak OBEROI - New Delhi, IN

G10L 13/047
G10L 13/033
G10L 17/22
G10L 17/06

Systems are configured for generating text-to-speech data in a personalized voice by training a neural text-to-speech machine learning model on natural speech data collected from a particular user, validating the identity of the user from which data is collected, and authorizing requests from users to use the personalized voice in generating new speech data. The systems are further configured to train a machine learning model as a neural text-to-speech model with generated personalized speech data.

20210225357, Jul 22, 2021

Jun 7, 2017

16/309399

- Redmond WA, US
Kaisheng YAO - Redmond WA, US
Max LEUNG - Redmond WA, US
Bo YAN - Redmond WA, US
Jian LUAN - Redmond WA, US
Yu SHI - Redmond WA, US
Malone MA - Redmond WA, US
Mei-Yuh HWANG - Redmond WA, US

MICROSOFT TECHNOLOGY LICENSING, LLC - Redmond WA

G10L 13/027
G10L 13/08
G10L 15/26
G10L 15/18
G06F 3/16
G10L 15/22
G10L 25/63
G10L 15/06

An example intent-recognition system comprises a processor and memory storing instructions. The instructions cause the processor to receive speech input comprising spoken words. The instructions cause the processor to generate text results based on the speech input and generate acoustic feature annotations based on the speech input. The instructions also cause the processor to apply an intent model to the text result and the acoustic feature annotations to recognize an intent based on the speech input. An example system for adapting an emotional text-to-speech model comprises a processor and memory. The memory stores instructions that cause the processor to receive training examples comprising speech input and receive labelling data comprising emotion information associated with the speech input. The instructions also cause the processor to extract audio signal vectors from the training examples and generate an emotion-adapted voice font model based on the audio signal vectors and the labelling data.

20150364127, Dec 17, 2015

Jun 13, 2014

14/303934

- Redmond WA, US
Kaisheng Yao - Newcastle WA, US
Max Leung - Beijing, CN
Mei-Yuh Hwang - Bellevue WA, US
Sheng Zhao - Beijing, CN
Bo Yan - Union City CA, US
Geoffrey Zweig - Sammamish WA, US
Fileno A. Alleva - Redmond WA, US

MICROSOFT CORPORATION - Redmond WA

G10L 13/08
G06N 3/02

The technology relates to performing letter-to-sound conversion utilizing recurrent neural networks (RNNs). The RNNs may be implemented as RNN modules for letter-to-sound conversion. The RNN modules receive text input and convert the text to corresponding phonemes. In determining the corresponding phonemes, the RNN modules may analyze the letters of the text and the letters surrounding the text being analyzed. The RNN modules may also analyze the letters of the text in reverse order. The RNN modules may also receive contextual information about the input text. The letter-to-sound conversion may then also be based on the contextual information that is received. The determined phonemes may be utilized to generate synthesized speech from the input text.

20150364128, Dec 17, 2015

Jun 13, 2014

14/303969

- Redmond WA, US
Max Leung - Beijing, CN
Kaisheng Yao - Newcastle WA, US
Bo Yan - Union City CA, US
Sheng Zhao - Beijing, CN
Fileno A. Alleva - Redmond WA, US

MICROSOFT CORPORATION - Redmond WA

G10L 13/08
G06N 3/02

The technology relates to converting text to speech utilizing recurrent neural networks (RNNs). The recurrent neural networks may be implemented as multiple modules for determining properties of the text. In embodiments, a part-of-speech RNN module, letter-to-sound RNN module, a linguistic prosody tagger RNN module, and a context awareness and semantic mining RNN module may all be utilized. The properties from the RNN modules are processed by a hyper-structure RNN module that determine the phonetic properties of the input text based on the outputs of the other RNN modules. The hyper-structure RNN module may generate a generation sequence that is capable of being converting to audible speech by a speech synthesizer. The generation sequence may also be optimized by a global optimization module prior to being synthesized into audible speech.