SPE-L10: Speech Recognition: Confidence, Errors and OOVs |
| Session Type: Lecture |
| Time: Thursday, 7 May, 09:00 - 11:00 |
| Location: On-Demand |
| Virtual Session: View on Virtual Platform |
| Session Chair: Florian Metze, Facebook |
| SPE-L10.1: ON MODELING ASR WORD CONFIDENCE |
| Woojay Jeon; Apple |
| Maxwell Jordan; Apple |
| Mahesh Krishnamoorthy; Apple |
| SPE-L10.2: CONFIDENCE ESTIMATION FOR BLACK BOX AUTOMATIC SPEECH RECOGNITION SYSTEMS USING LATTICE RECURRENT NEURAL NETWORKS |
| Alexandros Kastanos; University of Cambridge |
| Anton Ragni; University of Sheffield |
| Mark Gales; University of Cambridge |
| SPE-L10.3: OOV RECOVERY WITH EFFICIENT 2ND PASS DECODING AND OPEN-VOCABULARY WORD-LEVEL RNNLM RESCORING FOR HYBRID ASR |
| Xiaohui Zhang; Johns Hopkins University |
| Daniel Povey; Johns Hopkins University |
| Sanjeev Khudanpur; Johns Hopkins University |
| SPE-L10.4: END TO END SPEECH RECOGNITION ERROR PREDICTION WITH SEQUENCE TO SEQUENCE LEARNING |
| Prashant Serai; Ohio State University |
| Adam Stiff; Ohio State University |
| Eric Fosler-Lussier; Ohio State University |
| SPE-L10.5: ASR ERROR CORRECTION AND DOMAIN ADAPTATION USING MACHINE TRANSLATION |
| Anirudh Mani; Abridge AI |
| Shruti Palaskar; Carnegie Mellon University |
| Nimshi Venkat Meripo; Abridge AI |
| Sandeep Konam; Abridge AI |
| Florian Metze; Carnegie Mellon University |
| SPE-L10.6: JOINT CONTEXTUAL MODELING FOR ASR CORRECTION AND LANGUAGE UNDERSTANDING |
| Yue Weng; Uber Technologies Inc |
| Sai Sumanth Miryala; Uber Technologies Inc |
| Chandra Khatri; Uber Technologies Inc |
| Runze Wang; Uber Technologies Inc |
| Huaixiu Zheng; Uber Technologies Inc |
| Piero Molino; Uber Technologies Inc |
| Mahdi Namazifar; Uber Technologies Inc |
| Alexandros Papangelis; Uber Technologies Inc |
| Hugh Williams; Uber Technologies Inc |
| Franziska Bell; Uber Technologies Inc |
| Gokhan Tur; Uber Technologies Inc |