Inventor

WU YONGHUI

US63 patents

⚠️ This page may combine multiple inventors who share the name “WU YONGHUI”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

WU YONGHUI

GOOGLE LLC

Multi-dialect and multilingual speech recognition

Minimum word error rate training for attention-based sequence-to-sequence models

Multilingual speech synthesis and cross-language voice cloning

Minimum word error rate training for attention-based sequence-to-sequence models

Multi-dialect and multilingual speech recognition

Speech recognition with sequence-to-sequence models

Machine translation using neural network models

Implicit bridging of machine learning tasks

End-to-end text-to-speech conversion

Direct speech-to-speech translation via machine learning

Machine translation using neural network models

Synthesis of speech from text in a voice of a target speaker using neural networks

Synthesizing speech from text using neural networks

Implicit bridging of machine learning tasks

Generating descriptive text for images in documents using seed descriptors

Large-scale multilingual speech recognition with a streaming end-to-end model

Speech recognition with sequence-to-sequence models

Asynchronous distributed data flow for machine learning workloads

Selective text prediction for electronic messaging

Parallel tacotron non-autoregressive and controllable TTS

Multi-dialect and multilingual speech recognition

Synthesis of speech from text in a voice of a target speaker using neural networks

Synthesizing speech from text using neural networks

Multilingual speech synthesis and cross-language voice cloning

Phonemes and graphemes for neural text-to-speech

Minimum word error rate training for attention-based sequence-to-sequence models

Synthesis of speech from text in a voice of a target speaker using neural networks

Machine translation using neural network models

Unsupervised parallel tacotron non-autoregressive and controllable text-to-speech

End-to-end text-to-speech conversion

Speech recognition with sequence-to-sequence models

Parallel tacotron non-autoregressive and controllable TTS

End-to-end text-to-speech conversion

Unsupervised parallel tacotron non-autoregressive and controllable text-to-speech

End-to-end text-to-speech conversion

Convolution-augmented transformer models

Convolution-augmented transformer models

Building a text-to-speech system from a small amount of speech data

Asynchronous distributed data flow for machine learning workloads

Training of large neural networks

GOOGLE INC

Query generation using structural similarity between documents

Query generation using structural similarity between documents

Generating synthetic descriptive text

ZATSMAN MISHA

Framework for evaluating web search scoring functions

Framework for evaluating web search scoring functions

SHENZHEN GOODIX TECH CO LTD

Fingerprint identification device, method and electronic device

Fingerprint identification device, method and electronic device

FUTUREWEI TECHNOLOGIES INC

Methods of representing software defined networking-based multiple layer network topology views

BAKER STEVEN D

Query generation using structural similarity between documents

ARRIS ENTPR LLC

Providing Wi-Fi protected setup (WPS) by sending a code to a network device using a phone