Learn Before
Case Study

Choosing an End-to-End Model for Meeting Transcription

Case context: You are building a system that converts recorded team meetings into written transcripts. You have thousands of training examples, each consisting of an audio recording and the correct transcript.

Question: Why might an end-to-end learning approach be a strong choice for this project?

Sample answer: An end-to-end approach is a good fit because the task naturally provides labeled input-output pairs: meeting audio as input and the transcript as output. When enough paired data is available, the model can learn to map directly from sound to text without needing many hand-designed intermediate steps.

Key points:

  • The training data contains matched input-output pairs.
  • The model can learn a direct audio-to-text mapping.
  • End-to-end methods are well suited when enough labeled examples are available.

Rubric: The response must recommend an end-to-end approach, connect that choice to the availability of paired audio and transcript data, and explain that the model can learn the direct mapping from input to output.

0

1

Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI