Inventor

ROBLEK DOMINIK

CH78 patents

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

ROBLEK DOMINIK

GOOGLE LLC

Speaker identification using a text-independent model and a text-dependent model

Frequency based audio analysis using neural networks

Compressing audio waveforms using neural networks and vector quantizers

Segment-based speaker verification using dynamically generated phrases

Aggregation of related media content

Personalized entity repository

Segment-based speaker verification using dynamically generated phrases

Audio processing with neural networks

Dynamic display of content consumption by geographic location

Aggregation of related media content

Segment-based speaker verification using dynamically generated phrases

Audio data classification

Aggregation on related media content

Self-supervised pitch estimation

Determining that audio includes music and then identifying the music as a particular song

Identifying music as a particular song

Audio processing with neural networks

Segment-based speaker verification using dynamically generated phrases

GOOGLE INC

Dual model speaker identification

Large-scale speaker identification

Efficient utterance-specific endpointer triggering for always-on hotwording

Segment-based speaker verification using dynamically generated phrases

Segment-based speaker verification using dynamically generated phrases

Unified recognition of speech and music

Personalized entity repository

Text-dependent speaker identification

Segment-based speaker verification using dynamically generated phrases

Incentive-based check-in

Melody recognition systems

Segmenting content displayed on a computing device into regions based on pixels of a screenshot image that captures the content

Generating correlation scores

Hold back and real time ranking of results in a streaming matching system

Compressed patch features for audio fingerprinting

Reference signal suppression in speech recognition

Hold back and real time ranking of results in a streaming matching system

SHARIFI MATTHEW

Transformation invariant media matching

Audio matching using time alignment, frequency alignment, and interest point overlap to filter false positives

Dynamic display of content consumption by geographic location

Magnitude ratio descriptors for pitch-resistant audio matching

Ensemble interest point detection for audio matching

Frequency ratio fingerprint characterization for audio matching

Intelligent interest point pruning for audio matching

Min/max filter for audio matching

WISEMAN MATTHEW

Inverted client-side fingerprinting and matching

Real-time audio recognition protocol

Real-time audio recognition using multiple recognizers

Interface for real-time audio recognition

MATIAS YOSSI

Aggregation of related media content

TZANETAKIS GEORGE

Noise based interest point density pruning

ROBLEK DOMINIK

Interest points density control for audio matching