DeepAI AI Chat
Log In Sign Up

Learning To Detect Keyword Parts And Whole By Smoothed Max Pooling

by   Hyun-Jin Park, et al.

We propose smoothed max pooling loss and its application to keyword spotting systems. The proposed approach jointly trains an encoder (to detect keyword parts) and a decoder (to detect whole keyword) in a semi-supervised manner. The proposed new loss function allows training a model to detect parts and whole of a keyword, without strictly depending on frame-level labeling from LVCSR (Large vocabulary continuous speech recognition), making further optimization possible. The proposed system outperforms the baseline keyword spotting model in [1] due to increased optimizability. Further, it can be more easily adapted for on-device learning applications due to reduced dependency on LVCSR.


page 1

page 2

page 3

page 4


To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinement

Keyword spotting systems continuously process audio streams to detect ke...

Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting

We propose a max-pooling based loss function for training Long Short-Ter...

Latency Control for Keyword Spotting

Conversational agents commonly utilize keyword spotting (KWS) to initiat...

Towards visually prompted keyword localisation for zero-resource spoken languages

Imagine being able to show a system a visual depiction of a keyword and ...

Efficient keyword spotting using dilated convolutions and gating

We explore the application of end-to-end stateless temporal modeling to ...

Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting

Speech recognition is a sequence prediction problem. Besides employing v...

Optimize what matters: Training DNN-HMM Keyword Spotting Model Using End Metric

Deep Neural Network–Hidden Markov Model (DNN-HMM) based methods have bee...