Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
arXiv:2107.04289
Abstract
End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation. In this paper, we proposed to use a predicted loss that estimates the uncertainty of the sample. The CTC (Connectionist Temporal Classification) and attention loss are informative for speech recognition since they are computed based on all decoding paths and alignments. We defined an end-to-end active learning pipeline, training an ASR/LP (Automatic Speech Recognition/Loss Prediction) joint model. The proposed approach was validated on an English and a Chinese speech recognition task. The experiments show that our approach achieves competitive results, outperforming random selection, least confidence, and estimated loss method.
arXiv commentAccepted to IJCNN 2021
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Cost-Effective Active Learning for Deep Image Classification
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
- Listen, Attend and Spell
- ESPnet: End-to-End Speech Processing Toolkit
- Active Learning for Speech Recognition: the Power of Gradients
- Integrating Informativeness, Representativeness and Diversity in Pool-Based Sequential Active Learning for Regression