Low-frequency Compensated Synthetic Impulse Responses for Improved Far-field Speech Recognition

Abstract

We propose a method for generating low-frequency compensated synthetic impulse responses that improve the performance of far-field speech recognition systems trained on artificially augmented datasets. We design linear-phase filters that adapt the simulated impulse responses to equalization distributions corresponding to real-world captured impulse responses. Our filtered synthetic impulse responses are then used to augment clean speech data from LibriSpeech dataset [1]. We evaluate the performance of our method on the real-world LibriSpeech test set. In practice, our low-frequency compensated synthetic dataset can reduce the word-error-rate by up to 8.8% for far-field speech recognition.

Accepted to ICASSP 2020

References in corpus (5)

• Building and Evaluation of a Real Room Impulse Response Dataset
• Regression and Classification for Direction-of-Arrival Estimation with Convolutional Recurrent Neural Networks
• Scene-Aware Audio Rendering via Deep Acoustic Analysis
• Improving Reverberant Speech Training Using Diffuse Acoustic Simulation
• Interactive Sound Rendering on Mobile Devices using Ray-Parameterized Reverberation Filters

Cited by in corpus (5)

• Scene-Aware Audio Rendering via Deep Acoustic Analysis
• Improving Reverberant Speech Training Using Diffuse Acoustic Simulation
• Sound Synthesis, Propagation, and Rendering: A Survey
• Scene-aware Far-field Automatic Speech Recognition
• A study on more realistic room simulation for far-field keyword spotting