From 8f1018ff26ca679214ffab62ea987a2c2568e958 Mon Sep 17 00:00:00 2001 From: VladKha Date: Wed, 4 Jul 2018 14:04:48 +0300 Subject: [PATCH] More edits in "Trigger Word Detection" --- 5- Sequence Models/Readme.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/5- Sequence Models/Readme.md b/5- Sequence Models/Readme.md index b43598e1..0912f1ac 100644 --- a/5- Sequence Models/Readme.md +++ b/5- Sequence Models/Readme.md @@ -930,8 +930,8 @@ Here are the course summary as its given on the course [link](https://www.course - Y will be labels 0 or 1. 0 represents the non-trigger word, while 1 is that trigger word that we need to detect. - The model architecture can be like this: ![](Images/80.png) - - The vertical lines in the audio clip represent the trigger words. The corresponding to this will be 1. - - One disadvantage of this is the imbalanced dataset outputs. There will be a lot of zeros and few ones. + - The vertical lines in the audio clip represent moment just after the trigger word. The corresponding to this will be 1. + - One disadvantage of this creates a very imbalanced training set. There will be a lot of zeros and few ones. - A hack to solve this is to make an output a few ones for several times or for a fixed period of time before reverting back to zero. ![](Images/81.png) ![](Images/85.png)