| Clean Text and Full-Body Transformer: Microsoft's Submission to the WMT22 Shared Task on Sign Language Translation | Oct 24, 2022 | Action RecognitionLip Reading | —Unverified | 0 |
| Don't Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation | Oct 24, 2022 | SegmentationSpeech-to-Text | CodeCode Available | 0 |
| Does Joint Training Really Help Cascaded Speech Translation? | Oct 24, 2022 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | CodeCode Available | 0 |
| Bilingual Synchronization: Restoring Translational Relationships with Editing Operations | Oct 24, 2022 | Machine TranslationTranslation | CodeCode Available | 0 |
| Specializing Multi-domain NMT via Penalizing Low Mutual Information | Oct 24, 2022 | Machine TranslationNMT | —Unverified | 0 |
| Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech | Oct 24, 2022 | automatic-speech-translationTranslation | —Unverified | 0 |
| Analyzing the Use of Influence Functions for Instance-Specific Data Filtering in Neural Machine Translation | Oct 24, 2022 | image-classificationImage Classification | —Unverified | 0 |
| Focused Concatenation for Context-Aware Neural Machine Translation | Oct 24, 2022 | DecoderMachine Translation | CodeCode Available | 0 |
| Translation Word-Level Auto-Completion: What can we achieve out of the box? | Oct 23, 2022 | Machine TranslationSentence | CodeCode Available | 0 |
| VP-SLAM: A Monocular Real-time Visual SLAM with Points, Lines and Vanishing Points | Oct 23, 2022 | Simultaneous Localization and MappingTranslation | —Unverified | 0 |
