Inventor

MENGIBAR PEDRO J MORENO

US47 patents

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

MENGIBAR PEDRO J MORENO

GOOGLE LLC

Multi-dialect and multilingual speech recognition

Speech recognition using unspoken text and speech synthesis

Advancing the use of text and speech in ASR pretraining with consistency and contrastive losses

Voice recognition system

Language model biasing modulation

Voice recognition system

Customized voice action system

Voice recognition system

Classification of offensive words

Injecting text in self-supervised speech pre-training

Speech recognition using unspoken text and speech synthesis

Contextual denormalization for automatic speech recognition

Speech recognition using unspoken text and speech synthesis

Contextual denormalization for automatic speech recognition

Synthesized data augmentation using voice conversion and speech recognition models

Speech recognition with selective use of dynamic language models

Alignment prediction to inject text into automatic speech recognition training

Language model biasing modulation

Server side hotwording

Negative n-gram biasing

Determining dialog states for language models

Server side hotwording

Multi-dialect and multilingual speech recognition

Speech recognition

Multilingual re-scoring models for automatic speech recognition

Multilingual re-scoring models for automatic speech recognition

Chunk-wise attention for longform ASR

Sub-models for neural contextual biasing

Conformer-based speech conversion model

Self-adaptive distillation

GOOGLE INC

Evaluating transcriptions with a semantic parser

Generating speech data collection prompts

Contextual speech recognition

Determining advertisements based on verbal inputs to applications on a computing device

Dynamic language model

Language modeling in speech recognition

Mining data for natural language system

Methods and systems for speech recognition processing using search query information

Customized voice action system

Customized voice action system

Methods and systems for speech recognition processing using search query information

Dynamic language model

Increasing semantic coverage with semantically irrelevant insertions

MENGIBAR PEDRO J MORENO

Methods and systems for providing speech recognition systems based on speech recordings logs

Customized voice action system

Environmentally aware speech recognition

EPSTEIN MARK EDWARD

Methods and systems for determining instructions for applications that are recognizable by a voice interface