71 citations · 117 across the 14 of their papers we have counts for
16 papers
Logbook: Extremely Long-form Audio Event Understanding
Kwanghee Choi, Suwon Shon, Dmitriy Serdyuk +7
Audio benchmarks are built around short, pre-segmented clips, limiting model design to brief inputs or fixed vocabularies. To close this gap, we introduce Logbook, a benchmark for…
Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation
Sreyan Ghosh, Mohammad Sadegh Rasooli, Michael Levit +4
Generative Error Correction (GEC) has emerged as a powerful post-processing method to enhance the performance of Automatic Speech Recognition (ASR) systems. However, we show that G…
External Language Model Integration for Factorized Neural Transducers
Michael Levit, Sarangarajan Parthasarathy, Cem Aksoylar +2
We propose an adaptation method for factorized neural transducers (FNT) with external language models. We demonstrate that both neural and n-gram external LMs add significantly mor…
Bidirectional Language Models Are Also Few-shot Learners
Ajay Patel, Bryan Li, Mohammad Sadegh Rasooli +3
Large language models such as GPT-3 (Brown et al., 2020) can perform arbitrary tasks without undergoing fine-tuning after being prompted with only a few labeled examples. An arbitr…
Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation
Bryan Li, Mohammad Sadegh Rasooli, Ajay Patel +1
We propose a two-stage approach for training a single NMT model to translate unseen languages both to and from English. For the first stage, we initialize an encoder-decoder model…
"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks
Mohammad Sadegh Rasooli, Chris Callison-Burch, Derry Tanti Wijaya
We present a simple but effective approach for leveraging Wikipedia for neural machine translation as well as cross-lingual tasks of image captioning and dependency parsing without…