Efficient Utilization of Large Pre-Trained Models for Low Resource ASR

RWTH Publications (RWTH Aachen)

Abstract

Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and applications give rise to the question how to take advantage of large pre-trained models efficiently and reduce their complexity. In this work, we study a challenging low resource conversational telephony speech corpus from the medical domain in Vietnamese and German. We show the benefits of using unsupervised techniques beyond simple fine-tuning of large pre-trained models, discuss how to adapt them to a practical telephony task including bandwidth transfer and investigate different data conditions for pre-training and fine-tuning. We outperform the project baselines by 22% relative using pretraining techniques. Further gains of 29% can be achieved by refinements of architecture and training and 6% by adding 0.8 h of in-domain adaptation data.

Authors 3

1. Peter Vieting Aachen Human Language Technology and Pattern Recognition Group Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   Human Language Technology and Pattern Recognition Group , Computer Science Department , RWTH Aachen University , 52074 Aachen , Germany

2. Ralf Schlüter
3. Hermann Ney Aachen AppTek GmbH Human Language Technology and Pattern Recognition Group Computer Science Department

   RWTH Aachen University · FH Aachen

   Affiliation as printed

   AppTek GmbH , 52062 Aachen , Germany

   Human Language Technology and Pattern Recognition Group , Computer Science Department , RWTH Aachen University , 52074 Aachen , Germany