Trainable Frontend For Robust and Far-Field Keyword Spotting

07/19/2016
by   Yuxuan Wang, et al.
0

Robust and far-field speech recognition is critical to enable true hands-free communication. In far-field conditions, signals are attenuated due to distance. To improve robustness to loudness variation, we introduce a novel frontend called per-channel energy normalization (PCEN). The key ingredient of PCEN is the use of an automatic gain control based dynamic compression to replace the widely used static (such as log or root) compression. We evaluate PCEN on the keyword spotting task. On our large rerecorded noisy and far-field eval sets, we show that PCEN significantly improves recognition performance. Furthermore, we model PCEN as neural network layers and optimize high-dimensional PCEN parameters jointly with the keyword spotting acoustic model. The trained PCEN frontend demonstrates significant further improvements without increasing model complexity or inference-time cost.

READ FULL TEXT
research
02/06/2020

Robust Multi-channel Speech Recognition using Frequency Aligned Network

Conventional speech enhancement technique such as beamforming has known ...
research
09/13/2023

Open-vocabulary Keyword-spotting with Adaptive Instance Normalization

Open vocabulary keyword spotting is a crucial and challenging task in au...
research
10/30/2018

JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental Analysis

Used for simple commands recognition on devices from smart routers to mo...
research
11/01/2019

Long-distance Detection of Bioacoustic Events with Per-channel Energy Normalization

This paper proposes to perform unsupervised detection of bioacoustic eve...
research
08/12/2021

Dereverberation of Autoregressive Envelopes for Far-field Speech Recognition

The task of speech recognition in far-field environments is adversely af...
research
09/15/2021

Behavior of Keyword Spotting Networks Under Noisy Conditions

Keyword spotting (KWS) is becoming a ubiquitous need with the advancemen...
research
06/04/2020

A study on more realistic room simulation for far-field keyword spotting

We investigate the impact of more realistic room simulation for training...

Please sign up or login with your details

Forgot password? Click here to reset