Work

Transfer Learning for Speech Recognition on a Budget

Year: 2017
Type: conference-paper
Abstract: End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources.We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory, throughput and training data.We conduct several systematic experiments adapting a Wav2Letter convolutional neural network originally trained for English ASR to the German language.We show that this technique allows faster training on consumer-grade resources while requiring less training data in order to achieve the same accuracy, thereby lowering the cost of training ASR models in other languages.Model introspection revealed that small adaptations to the network's weights were sufficient for good performance, especially for inner layers.
Language: English
Open Access status: hybrid
Funder: Nvidia
OpenAlex ID: W2620869433
FWCI: 3.588
Cites: 24
Cited by: 180
Related to: 10