Inventor · disambiguated record
Rohit Prakash Prabhavalkar
Also filed as: PRABHAVALKAR ROHIT · PRABHAVALKAR ROHIT PRAKASH
33 granted patents·9 pending applications·130 citations·filing 2015–2025
96Inventor score
Top patents by PatentIndex Score
42 records- 0198US11646019B2Minimum word error rate training for attention-based sequence-to-sequence modelsGOOGLE LLC·Filed 2021·Granted May 9, 2023·10 cites·18 claims
- 0297US11217231B2Contextual biasing for speech recognition using grapheme and phoneme dataGOOGLE LLC·Filed 2020·Granted Jan 4, 2022·8 cites·30 claims
- 0396US11423883B2Contextual biasing for speech recognitionGOOGLE LLC·Filed 2020·Granted Aug 23, 2022·7 cites·28 claims
- 0496US11270687B2Phoneme-based contextualization for cross-lingual speech recognition in end-to-end modelsGOOGLE LLC·Filed 2020·Granted Mar 8, 2022·6 cites·18 claims
- 0594US11908461B2Deliberation model-based two-pass end-to-end speech recognitionGOOGLE LLC·Filed 2021·Granted Feb 20, 2024·4 cites·26 claims
- 0694US11741966B2Automated calling systemGOOGLE LLC·Filed 2022·Granted Aug 29, 2023·3 cites·20 claims
- 0794US9443517B1Generating sounds for detectability by neural networksGOOGLE INC·Filed 2015·Granted Sep 13, 2016·31 cites·20 claims
- 0893US12051407B2Contextual biasing for speech recognitionGOOGLE LLC·Filed 2022·Granted Jul 30, 2024·2 cites·20 claims
- 0993US11610586B2Learning word-level confidence for subword end-to-end automatic speech recognitionGOOGLE LLC·Filed 2021·Granted Mar 21, 2023·6 cites·28 claims
- 1092US11495233B2Automated calling systemGOOGLE LLC·Filed 2021·Granted Nov 8, 2022·4 cites·20 claims
- 1192US11145293B2Speech recognition with sequence-to-sequence modelsGOOGLE LLC·Filed 2019·Granted Oct 12, 2021·12 cites·20 claims
- 1292US11107463B2Minimum word error rate training for attention-based sequence-to-sequence modelsGOOGLE LLC·Filed 2019·Granted Aug 31, 2021·10 cites·17 claims
- 1391US11948570B2Key phrase spottingGOOGLE LLC·Filed 2022·Granted Apr 2, 2024·2 cites·20 claims
- 1491US11295739B2Key phrase spottingGOOGLE LLC·Filed 2019·Granted Apr 5, 2022·12 cites·15 claims
- 1590US11990133B2Automated calling systemGOOGLE LLC·Filed 2023·Granted May 21, 2024·1 cites·18 claims
- 1689US12027158B2Deliberation model-based two-pass end-to-end speech recognitionGOOGLE LLC·Filed 2023·Granted Jul 2, 2024·1 cites·18 claims
- 1787US11158321B2Automated calling systemGOOGLE LLC·Filed 2019·Granted Oct 26, 2021·5 cites·20 claims
- 1882US11475880B2Joint endpointing and automatic speech recognitionGOOGLE LLC·Filed 2020·Granted Oct 18, 2022·2 cites·26 claims
- 1980US11948062B2Compressed recurrent neural network modelsGOOGLE LLC·Filed 2020·Granted Apr 2, 2024·1 cites·22 claims
- 2080US2024379095A1Contextual biasing for speech recognitionGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2179US2024420686A1Speech recognition with sequence-to-sequence modelsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2277US10878319B2Compressed recurrent neural network modelsGOOGLE LLC·Filed 2016·Granted Dec 29, 2020·3 cites·15 claims
- 2375US12254883B2Automated calling systemGOOGLE LLC·Filed 2024·Granted Mar 18, 2025·0 cites·20 claims
- 2474US11922932B2Minimum word error rate training for attention-based sequence-to-sequence modelsGOOGLE LLC·Filed 2023·Granted Mar 5, 2024·0 cites·20 claims
- 2572US2025308512A1Deliberation by text-only and semi-supervised trainingGOOGLE LLC·Filed 2025·Application pending·0 cites
- 2672US2024221750A1Key phrase spottingGOOGLE LLC·Filed 2024·Application pending·0 cites
- 2771US12106749B2Speech recognition with sequence-to-sequence modelsGOOGLE LLC·Filed 2021·Granted Oct 1, 2024·0 cites·20 claims
- 2870US2023274736A1Contextual Biasing for Speech RecognitionGOOGLE LLC·Filed 2023·Application pending·0 cites
- 2969US11664021B2Contextual biasing for speech recognitionGOOGLE LLC·Filed 2021·Granted May 30, 2023·0 cites·20 claims
- 3067US12354595B2Deliberation by text-only and semi-supervised trainingGOOGLE LLC·Filed 2023·Granted Jul 8, 2025·0 cites·20 claims
- 3163US11942076B2Phoneme-based contextualization for cross-lingual speech recognition in end-to-end modelsGOOGLE LLC·Filed 2022·Granted Mar 26, 2024·0 cites·20 claims
- 3258US12444408B2Two-pass end to end speech recognitionGOOGLE LLC·Filed 2020·Granted Oct 14, 2025·0 cites·18 claims
- 3354US12154581B2Cascaded encoders for simplified streaming and non-streaming ASRGOOGLE LLC·Filed 2021·Granted Nov 26, 2024·0 cites·17 claims
- 3453US12488791B2Contextual biasing with text injectionGOOGLE LLC·Filed 2023·Granted Dec 2, 2025·0 cites·24 claims
- 3553US12417770B2Unified cascaded encoder ASR model for dynamic model sizesGOOGLE LLC·Filed 2023·Granted Sep 16, 2025·0 cites·19 claims
- 3653US2025078815A1Quantization and sparsity aware fine-tuning for speech recognition with universal speech modelsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 3752US2024304181A1Connecting different asr application domains with speaker-tagsGOOGLE LLC·Filed 2024·Application pending·0 cites
- 3852US2024028829A1Joint Speech and Text Streaming Model for ASRGOOGLE LLC·Filed 2023·Application pending·0 cites
- 3951US12354598B2Rare word recognition with LM-aware MWER trainingGOOGLE LLC·Filed 2023·Granted Jul 8, 2025·0 cites·24 claims
- 4051US2024185841A1Parameter-efficient model reprogramming for cross-lingual speech recognitionGOOGLE LLC·Filed 2023·Application pending·0 cites
- 4148US12340799B2Identifying and correcting automatic speech recognition (ASR) misrecognitions in a decentralized mannerGOOGLE LLC·Filed 2022·Granted Jun 24, 2025·0 cites·20 claims
- 4246US12482453B2Training for long-form speech recognitionGOOGLE LLC·Filed 2022·Granted Nov 25, 2025·0 cites·14 claims
Join the waitlist — get patent alerts
Get an alert when Rohit Prakash Prabhavalkar files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →