Light Gated Recurrent Units For Speech Recognition

Abstract

A field that has directly benefited from the recent advances in deep learning is Automatic Speech Recognition (ASR). Despite the great achievements of the past decades, however, a natural and robust human-machine speech interaction still appears to be out of reach, especially in challenging environments characterized by significant noise and reverberation. To improve robustness, modern speech recognizers often employ acoustic models based on Recurrent Neural Networks (RNNs), that are naturally able to exploit large time contexts and long-term speech modulations. It is thus of great interest to continue the study of proper techniques for improving the effectiveness of RNNs in processing speech signals. In this paper, we revise one of the most popular RNN models, namely Gated Recurrent Units (GRUs), and propose a simplified architecture that turned out to be very effective for ASR. The contribution of this work is two-fold: First, we analyze the role played by the reset gate, showing t

Stats

• citations330
• S2 citations—
• github stars0
• HF likes0
• heat score18.90
• arxiv keyravanelli2018light

Related papers

• Improving Speech Recognition By Revising Gated Recurrent Units (2017)11.19
• Stabilising And Accelerating Light Gated Recurrent Units For Automatic Speech Recognition (2023)0.00
• Memory Visualization For Gated Recurrent Neural Networks In Speech Recognition (2016)11.76
• Investigating Gated Recurrent Neural Networks For Speech Synthesis (2016)0.00
• Dynamic Gated Recurrent Neural Network For Compute-efficient Speech Enhancement (2024)8.35
• Gated Recurrent Unit Based Acoustic Modeling With Future Context (2018)7.16
• A Comparison Of Adaptation Techniques And Recurrent Neural Network Architectures (2018)3.58
• Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit (2020)4.52