Issued Patents All Time
Showing 1–21 of 21 patents
| Patent # | Title | Co-Inventors | Date |
|---|---|---|---|
| 12136415 | Mixture model attention for flexible streaming and non-streaming automatic speech recognition | Bhuvana Ramabhadran, Tongzhou Chen, Pedro J. Moreno Mengibar | 2024-11-05 |
| 12136411 | Training of model for processing sequence data | Gakuto Kurata | 2024-11-05 |
| 12106215 | Knowledge transfer between recurrent neural networks | Gakuto Kurata | 2024-10-01 |
| 12087279 | Regularizing word segmentation | Bhuvana Ramabhadran, Hainan Xu, Yinghui Huang | 2024-09-10 |
| 12014729 | Mixture model attention for flexible streaming and non-streaming automatic speech recognition | Bhuvana Ramabhadran, Tongzhou Chen, Pedro J. Moreno Mengibar | 2024-06-18 |
| 11929062 | End-to-end spoken language understanding without full transcripts | Hong-Kwang Kuo, Zoltan Tueske, Samuel Thomas, Yinghui Huang, Brian E. D. Kingsbury | 2024-03-12 |
| 11900922 | Multilingual intent recognition | Samuel Thomas, Hong-Kwang Kuo, Michael A. Picheny | 2024-02-13 |
| 11625595 | Knowledge transfer between recurrent neural networks | Gakuto Kurata | 2023-04-11 |
| 11587551 | Leveraging unpaired text data for training end-to-end spoken language understanding systems | Hong-Kwang Kuo, Yinghui Huang, Samuel Thomas, Michael A. Picheny | 2023-02-21 |
| 11568858 | Transliteration based data augmentation for training multilingual ASR acoustic models in low resource settings | Samuel Thomas, Brian E. D. Kingsbury | 2023-01-31 |
| 11495213 | Noise speed-ups in hidden markov models with applications to speech recognition | Osonde Osoba, Bart Kosko | 2022-11-08 |
| 11404047 | Feature and feature variant reconstruction for recurrent model accuracy improvement in speech recognition | Gakuto Kurata | 2022-08-02 |
| 11302309 | Aligning spike timing of models for maching learning | Gakuto Kurata | 2022-04-12 |
| 11256982 | Noise-enhanced convolutional neural networks | Bart Kosko, Osonde Osoba | 2022-02-22 |
| 11183194 | Detecting and recovering out-of-vocabulary words in voice-to-text transcription systems | Samuel Thomas, Zoltan Tueske, Yinghui Huang, Michael A. Picheny | 2021-11-23 |
| 11158303 | Soft-forgetting for connectionist temporal classification based automatic speech recognition | George Andrei Saon, Zoltan Tueske, Brian E. D. Kingsbury, Michael A. Picheny | 2021-10-26 |
| 10839792 | Recognition of out-of-vocabulary in direct acoustics-to-word speech recognition using acoustic word embedding | Karen Livescu, Michael A. Picheny, Shane Settle | 2020-11-17 |
| 10692488 | Implementing a whole sentence recurrent neural network language model for natural language processing | Yinghui Huang, Abhinav Sethy, Bhuvana Ramabhadran | 2020-06-23 |
| 10431210 | Implementing a whole sentence recurrent neural network language model for natural language processing | Yinghui Huang, Abhinav Sethy, Bhuvana Ramabhadran | 2019-10-01 |
| 10019438 | External word embedding neural network language models | Bhuvana Ramabhadran, Abhinav Sethy | 2018-07-10 |
| 8457967 | Automatic evaluation of spoken fluency | Om D. Deshmukh, Kundan Kandhway, Ashish Verma | 2013-06-04 |