AI-102 Practice Question: Implement natural language processing solutions
A company uses Azure AI Speech for real-time captioning during live events. They notice a delay of 5 seconds between speech and caption display. Which action should they take to reduce latency?
⚠ Common exam trap
A common mix-up: candidates confuse latency reduction with accuracy improvements, incorrectly assuming that a custom model or more alternatives will speed up processing, when in fact the solution lies in changing the result delivery mode from final-only to streaming partial results.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Use the Speech SDK with intermediate results enabled
Enabling intermediate results in the Speech SDK allows the client to receive partial, real-time recognition hypotheses as the audio is being processed, rather than waiting for the final, fully processed result. This reduces the perceived latency from the full utterance duration (which can be several seconds) to near-instantaneous display of partial captions, directly addressing the 5-second delay.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Deploy a custom speech model
Why it's wrong here
A custom speech model improves recognition accuracy for domain vocabulary or accents, not pipeline latency. The five-second delay stems from buffering and transport; streaming transcription with reduced chunk sizes addresses that, whereas custom models would be chosen for poor word error rates.
- ✓
Use the Speech SDK with intermediate results enabled
Why this is correct
Enabling intermediate results streams partial transcriptions as recognition progresses, rather than waiting for final utterance boundaries. This directly addresses the five-second delay constraint by surfacing captions before endpoint detection completes, cutting perceived latency for live captioning.
- ✗
Switch to batch transcription API
Why it's wrong here
Batch transcription submits audio and returns results asynchronously, typically after the job completes, so it cannot support live captioning at all. It is the right choice for transcribing archived recordings, not for reducing delay in a real-time stream.
- ✗
Increase the maxAlternatives parameter
Why it's wrong here
maxAlternatives controls how many candidate transcriptions the recogniser returns per utterance; raising it adds processing work and can increase delay. It is used when you need confidence-ranked alternatives, not for latency tuning of live captioning.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.