Learn Before
A Multi-Stage Speech Recognition System
One way to build a speech recognizer is to first extract MFCC features from audio, then predict a sequence of phonemes, and finally convert those phonemes into the written transcript.
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
When a Driving Pipeline Lacks the Right Information
Domain-Designed Features Can Lower the Amount of Training Data Needed
Choosing Steps and Connections in a Pipeline
Learned and Non-Learned Pipeline Components
If a hospital intake system has highly accurate symptom and risk classifiers, its end-to-end patient routing must also be highly accurate.
A multi-stage system works only if you can _____ enough labeled examples for each component.
Three Ideas in a Machine Learning Pipeline
How to Rework a Multi-Stage Machine Learning Pipeline
When a Multi-Stage Pipeline Hides Missing Information
Case Study: Diagnosing a Parcel-Delivery Drone Pipeline
Non-Learning Components in a Robotics Pipeline
When Does a Multi-Stage System Make Sense?
Pipelines Can Include Branching Steps
Handcrafted Stages Can Cap Overall System Quality
Learn After
What does MFCC feature extraction mainly try to retain in a speech-recognition system?
In a two-stage speech recognizer, does the second stage use predicted phoneme labels rather than raw MFCC frames?
The speech system identifies the smallest distinct units of sound called _____.
Match each speech system element to its role.
Order the steps in a voice-to-text pipeline.
Describe the flow of information in a three-step speech recognition system.
Find the failing stage when the alerts are right but the bulletin is wrong
What do the initial sounds in “meter” and “music” reveal about phonemes?
What does the final stage receive as input in this speech pipeline?
In a bird-call analysis pipeline, the final report can be written before the calls are identified into species labels.