| Presentation # | 2 |
| Session: | Corpora and Evaluation Methodologies |
| Location: | Kallirhoe Hall |
| Session Time: | Wednesday, December 19, 13:30 - 15:30 |
| Presentation Time: | Wednesday, December 19, 13:30 - 15:30 |
| Presentation: |
Poster
|
| Topic: |
Spoken language corpora: |
| Paper Title: |
TOWARDS FLUENT TRANSLATIONS FROM DISFLUENT SPEECH |
| Authors: |
Elizabeth Salesky, Susanne Burger, Carnegie Mellon University, United States; Jan Niehues, Karlsruhe Institute of Technology, Germany; Alex Waibel, Carnegie Mellon University, United States |
| Abstract: |
When translating speech, special consideration for conversational speech phenomena such as disfluencies is necessary. Most machine translation training data consists of well-formed written texts, causing issues when translating spontaneous speech. Previous work has introduced an intermediate step between speech recognition (ASR) and machine translation (MT) to remove disfluencies, making the data better-matched to typical translation text and significantly improving performance. However, with the rise of end-to-end speech translation systems, this intermediate step must be incorporated into the sequence-to-sequence architecture. Further, though translated speech datasets exist, they are typically news or rehearsed speech without many disfluencies (e.g. TED), or the disfluencies are translated into the references (e.g. Fisher). To generate clean translations from disfluent speech, cleaned references are necessary for evaluation. We introduce a corpus of cleaned references for Fisher Spanish-English for this task. We compare how different architectures handle disfluencies, and provide a baseline for removing disfluencies in end-to-end translation. |