Pre-training in Deep Reinforcement Learning for Automatic Speech Recognition

2019/10/24 by Thejan Rajapakshe, Rajib Rana, Rajapakshe, Thejan +7
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Music and Audio Processing #Reinforcement Learning in Robotics #Sound (cs.SD) #Speech Recognition and Synthesis

paper · pdf · doi:10.48550/arxiv.1910.11256

openalex publication_date 2019/10/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep reinforcement learning (deep RL) is a combination of deep learning with reinforcement learning principles to create efficient methods that can learn by interacting with its environment. This led to breakthroughs in many complex tasks that were previously difficult to solve. However, deep RL requires a large amount of training time that makes it difficult to use in various real-life applications like human-computer interaction (HCI). Therefore, in this paper, we study pre-training in deep RL to reduce the training time and improve the performance in speech recognition, a popular application of HCI. We achieve significantly improved performance in less time on a publicly available speech command recognition dataset.

Citations

• Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences

Related

• Deep Reinforcement Learning with Pre-training for Time-efficient Training of Automatic Speech Recognition
• Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook
• Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection
• Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement Learning
• Explore the Reinforcement Learning for the LLM based ASR and TTS system