Speech Recognition Training Error Categories
For a speech recognition app with a training set of audio clips from volunteers, counted error categories can include loud background noise, a user speaking quickly, and being far from the microphone.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Speech Recognition Training Error Categories
When a learning algorithm performs poorly on the training set, what is the recommended first step?
True or False: Reviewing poor training examples involves categorizing and counting errors, similar to dev set error analysis.
If a system performs poorly on the training set, consider listening to about _____ examples the algorithm is doing poorly on.
Match each error analysis concept to its correct description in the context of reviewing training examples.
Order the steps for reviewing poor training examples when the system performs poorly on the training set.
Explain why reviewing ~100 poorly-performing training examples helps diagnose training set errors.
A team's training set accuracy is low; what should they do to diagnose the issue?
Briefly describe what to do when a system is not doing well on the training set.
What is the primary goal of listening to poorly-performing training examples?
True or False: The training set error review process described requires reviewing every single training example.
Learn After
Which counted category describes competing sound that makes a volunteer’s audio clip poor?
A volunteer speaking quickly can be counted as a training error category in this example.
Complete the category: Far from the _____.
Match each review label to the condition it records in a volunteer audio clip.
Order the process for categorizing a poor volunteer audio clip.
Explain how the listed categories structure a review of poor speech-recognition training clips.
Classify the applicable categories for a noisy clip recorded at a distance.
What three conditions can be counted when reviewing these volunteer audio clips?
Which label fits a poor clip with rapid speech but no noted noise or microphone-distance issue?
One volunteer clip may be marked for both noise and microphone distance when both are observed.