Hassan Sawaf

2 accepted papers

2023

EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only

Kamer Yüksel, Ahmet Gunduz, Mohamed Al-badrashiny, Hassan Sawaf

ACL 2023industry

This work proposes a method named EvolveMT for the efficient combination of multiple machine translation (MT) engines. The method selects the output from one engine for each segment, using online learning techniques to predict the most appropriate system for each translation request. A neural qualit…

Cited by 1 Source ↗PDF ↗Scholar ↗

2015

Switching to and combining offline-adapted cluster acoustic models based on unsupervised segment classification

Jintao Jiang, Hassan Sawaf

ICASSP 2015accepted

The performance of automatic speech recognition system degrades significantly when the incoming audio differs from training data. Maximum likelihood linear regression has been widely used for unsupervised adaptation, usually in a multiple-pass recognition process. Here we present a novel adaptation…

Cited by 0 Source ↗Scholar ↗