Search Results for author: Dirk Padfield

Found 7 papers, 1 papers with code

MultiTurnCleanup: A Benchmark for Multi-Turn Spoken Conversational Transcript Cleanup

1 code implementation19 May 2023 Hua Shen, Vicky Zayats, Johann C. Rocholl, Daniel D. Walker, Dirk Padfield

Current disfluency detection models focus on individual utterances each from a single speaker.

Sentence Boundary Augmentation For Neural Machine Translation Robustness

no code implementations21 Oct 2020 Daniel Li, Te I, Naveen Arivazhagan, Colin Cherry, Dirk Padfield

Specifically, in the context of long-form speech translation systems, where the input transcripts come from Automatic Speech Recognition (ASR), the NMT models have to handle errors including phoneme substitutions, grammatical structure, and sentence boundaries, all of which pose challenges to NMT robustness.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +7

Inverted Projection for Robust Speech Translation

no code implementations ACL (IWSLT) 2021 Dirk Padfield, Colin Cherry

Traditional translation systems trained on written documents perform well for text-based translation but not as well for speech-based applications.

Translation

Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection

no code implementations NAACL 2022 Angelica Chen, Vicky Zayats, Daniel D. Walker, Dirk Padfield

In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed.

Machine Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.