Active Learning Of Non-semantic Speech Tasks With Pretrained Models

Abstract

Pretraining neural networks with massive unlabeled datasets has become popular as it equips the deep models with a better prior to solve downstream tasks. However, this approach generally assumes that the downstream tasks have access to annotated data of sufficient size. In this work, we propose ALOE, a novel system for improving the data- and label-efficiency of non-semantic speech tasks with active learning. ALOE uses pretrained models in conjunction with active learning to label data incrementally and learn classifiers for downstream tasks, thereby mitigating the need to acquire labeled data beforehand. We demonstrate the effectiveness of ALOE on a wide range of tasks, uncertainty-based acquisition functions, and model architectures. Training a linear classifier on top of a frozen encoder with ALOE is shown to achieve performance similar to several baselines that utilize the entire labeled data.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keylee2022active

Related papers

• Boosting Active Learning For Speech Recognition With Noisy Pseudo-labeled Samples (2020)0.00
• Loss Prediction: End-to-end Active Learning Approach For Speech Recognition (2021)7.16
• Active Learning With Task Adaptation Pre-training For Speech Emotion Recognition (2024)5.84
• Unsupervised Transfer Learning For Spoken Language Understanding In Intelligent Agents (2018)0.00
• Active Learning Based Fine-tuning Framework For Speech Emotion Recognition (2023)6.34
• Leveraging In-the-wild Data For Effective Self-supervised Pretraining In Speaker Recognition (2023)3.58
• Fast End-to-end Speech Recognition Via Non-autoregressive Models And Cross-modal Knowledge Transferring From BERT (2021)12.93
• Unsupervised Active Learning: Optimizing Labeling Cost-effectiveness For Automatic Speech Recognition (2023)0.00