2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
| Paper ID | HLT-7.3 | ||
| Paper Title | JOINTLY TRAINED TRANSFORMERS MODELS FOR SPOKEN LANGUAGE TRANSLATION | ||
| Authors | Hari Krishna Vydana, BUT, Czechia; Martin Karafiat, Katerina Zmolikova, Lukáš Burget, Jan "Honza" Cernocky, Brno University of Technology, Czechia | ||
| Session | HLT-7: Speech Translation 1: Models | ||
| Location | Gather.Town | ||
| Session Time: | Wednesday, 09 June, 14:00 - 14:45 | ||
| Presentation Time: | Wednesday, 09 June, 14:00 - 14:45 | ||
| Presentation | Poster | ||
| Topic | Human Language Technology: [HLT-MTSW] Machine Translation for Spoken and Written Language | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | End-to-End and cascade (ASR-MT) spoken language translation (SLT) systems are reaching comparable performances, however, a large degradation is observed when translating the ASR hypothesis in comparison to using oracle input text. In this work, degradation in performance is reduced by creating an End-to-End differentiable pipeline between the ASR and MT systems. In this work, we train SLT systems with ASR objective as an auxiliary loss and both the networks are connected through the neural hidden representations. This training has an End-to-End differentiable path with respect to the final objective function and utilizes the ASR objective for better optimization. This architecture has improved the BLEU score from 41.21 to 44.69. Ensembling the proposed architecture with independently trained ASR and MT systems further improved the BLEU score from 44.69 to 46.9. All the experiments are reported on English-Portuguese speech translation task using the How2 corpus. The final BLEU score is on-par with the best speech translation system on How2 dataset without using any additional training data and language model and using much less parameters. | ||