Inventor

GONG YIFAN

US95 patents

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

GONG YIFAN

MICROSOFT TECHNOLOGY LICENSING LLC

Speaker-invariant training via adversarial learning

Low-footprint adaptation and personalization for a deep neural network

Multi-channel speech separation

Reduced size computerized speech model speaker adaptation

Domain adaptation in speech recognition via teacher-student learning

Advancing word-based speech recognition processing

Code-switching speech recognition with end-to-end connectionist temporal classification model

Adversarial teacher-student learning for unsupervised domain adaptation

Speaker recognition

Shared hidden layer combination for speech recognition systems

Pre-training with alignments for recurrent neural network transducer based end-to-end speech recognition

Machine learning model with depth processing units

Restructuring deep neural network acoustic models

Generating and using text-to-speech data for speech recognition models

Modular deep learning model

On-device custom wake word detection

Conditional teacher-student learning for model training

Universal acoustic modeling using neural mixture models

Learning student DNN via output distribution

Attentive adversarial domain-invariant training

Attentive adversarial domain-invariant training

Small-footprint deep neural network

Variable-component deep neural network for robust speech recognition

Speaker adaptation for attention-based encoder-decoder

Automatic speech recognition confidence classifier

TEXAS INSTRUMENTS INC

Method of speech recognition resistant to convolutive distortion and additive distortion

Method and system for adaptive speech recognition in a noisy environment

Method of adapting speech recognition models for speaker, microphone, and noisy environment

Method of speech recognition with compensation for both channel distortion and background noise

Source normalization training for HMM modeling of speech

Log-spectral compensation of PMC Gaussian mean vectors for noisy speech recognition using log-max assumption

Speech recognition front-end feature extraction for noisy speech

System and method of noise-dependent classification

Source normalization training for HMM modeling of speech

Method for transforming HMMs for speaker-independent recognition in a noisy environment

Accumulating transformations for hierarchical linear regression HMM adaptation

Automatic utterance detector with high noise immunity

Noise-resistant utterance detector

Method to extend operating range of joint additive and convolutive compensating algorithms

Sequential determination of utterance log-spectral mean by maximum a posteriori probability estimation

Implementing a high accuracy continuous speech recognizer on a fixed-point processor

MICROSOFT CORP

Exploiting heterogeneous data in deep neural network-based speech recognition systems

Multilingual deep neural network

Speech model refinement with transcription error detection

Feature space transformation for personalization using generalized i-vector clustering

LI JINYU

Adapting a compressed model for use in speech recognition

Model training for automatic speech recognition from imperfect transcription data

LIU CHAOJUN

Enhanced automatic speech recognition using mapping between unsupervised and supervised speech model parameters trained on same acoustic training data

CHU MIN

Identifying language origin of words

YU DONG

Noise suppressor for robust speech recognition