Inventor

BODAPATI SRAVAN BABU

US30 patents

Patents

30 patents

US11657307B1May 23, 2023

Data lake-based text generation and data augmentation for machine learning training

AMAZON TECH INC34 citations93

US11734937B1Aug 22, 2023

Federated learning service in a provider network and training machine learning models using devices external to the provider network

AMAZON TECH INC5 citations73

US12182498B1Dec 31, 2024

Redacting portions of text transcriptions generated from inverse text normalization

AMAZON TECH INC5 citations71

US11710479B1Jul 25, 2023

Contextual biasing of neural language models using metadata from a natural language understanding component and embedded recent history

AMAZON TECH INC3 citations71

US11580965B1Feb 14, 2023

Multimodal based punctuation and/or casing prediction

AMAZON TECH INC5 citations71

US11580379B1Feb 14, 2023

Phased deployment of deep-learning models to customer facing APIs

AMAZON TECH INC6 citations69

US12198681B1Jan 14, 2025

Personalized batch and streaming speech-to-text transcription of audio

AMAZON TECH INC4 citations68

US11861039B1Jan 2, 2024

Hierarchical system and method for identifying sensitive content in data

AMAZON TECH INC2 citations66

US9858257B1Jan 2, 2018

Distinguishing intentional linguistic deviations from unintentional linguistic deviations

AMAZON TECH INC3 citations65

US12250180B1Mar 11, 2025

Dynamically selectable automated speech recognition using a custom vocabulary

AMAZON TECH INC1 citations62

US11551695B1Jan 10, 2023

Model training system for custom speech-to-text models

AMAZON TECH INC2 citations62

US12321835B1Jun 3, 2025

Federated learning service in a provider network and training machine learning models using devices external to the provider network

AMAZON TECH INC0 citations61

US12400644B1Aug 26, 2025

Dynamic language model updates with boosting

AMAZON TECH INC0 citations59

US12136413B1Nov 5, 2024

Domain-specific parameter pre-fixes for tuning automatic speech recognition

AMAZON TECH INC1 citations58

US12505827B1Dec 23, 2025

Customizable latency for automatic speech recognition

AMAZON TECH INC0 citations55

US12562151B1Feb 24, 2026

Augmenting automated speech recognition neural networks with scalable vocabularies

AMAZON TECH INC0 citations46

US12400659B1Aug 26, 2025

Infusing knowledge graphs into automatic speech recognition

AMAZON TECH INC0 citations46

US12530525B1Jan 20, 2026

Autocomplete with deep retrieval reinforcement learning

AMAZON TECH INC0 citations45

US12586567B1Mar 24, 2026

Multi-domain fine-tuning for contextual adapters of automatic speech recognition

AMAZON TECH INC0 citations44

US12547841B2Feb 10, 2026

Medical conversation summarization style intelligence

AMAZON TECH INC0 citations43

US12387718B1Aug 12, 2025

Removing bias from automatic speech recognition models using internal language model estimates

AMAZON TECH INC0 citations42

US12205584B1Jan 21, 2025

Dialog-driven applications supporting alternative vocal input styles

AMAZON TECH INC0 citations41

BODAPATI SRAVAN BABU

Patents

Data lake-based text generation and data augmentation for machine learning training

Creating text classification machine learning models

Extending sensitive data tagging without reannotating training data

Automated identification of start-of-reading location for ebooks

Attention-based deep reinforcement learning for autonomous agents

Detecting whether a message is addressed to an intended recipient

Multi-label document classification for documents from disjoint class sets

Text de-obfuscation with image recognition of text

Managing access to sensitive data in transcriptions

Federated learning service in a provider network and training machine learning models using devices external to the provider network

Redacting portions of text transcriptions generated from inverse text normalization

Contextual biasing of neural language models using metadata from a natural language understanding component and embedded recent history

Multimodal based punctuation and/or casing prediction

Phased deployment of deep-learning models to customer facing APIs

Personalized batch and streaming speech-to-text transcription of audio

Hierarchical system and method for identifying sensitive content in data

Distinguishing intentional linguistic deviations from unintentional linguistic deviations

Dynamically selectable automated speech recognition using a custom vocabulary

Model training system for custom speech-to-text models

Federated learning service in a provider network and training machine learning models using devices external to the provider network

Dynamic language model updates with boosting

Domain-specific parameter pre-fixes for tuning automatic speech recognition

Customizable latency for automatic speech recognition

Augmenting automated speech recognition neural networks with scalable vocabularies

Infusing knowledge graphs into automatic speech recognition

Autocomplete with deep retrieval reinforcement learning

Multi-domain fine-tuning for contextual adapters of automatic speech recognition

Medical conversation summarization style intelligence

Removing bias from automatic speech recognition models using internal language model estimates

Dialog-driven applications supporting alternative vocal input styles