AI-102 Practice Question: Implement natural language processing solutions
A company uses Azure AI Speech to provide real-time transcription for customer support calls. The solution must handle multiple languages and filter out profanity. Which THREE configurations are needed?
⚠ Common exam trap
The trap is confusing batch and real-time APIs, and assuming custom models are needed for each language when built-in models suffice.
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
✓
Set the SpeechConfig.SpeechRecognitionLanguage property
Option C is correct because setting SpeechConfig.SpeechRecognitionLanguage specifies the recognition locale (for example, en-US or fr-FR) so the Speech SDK loads the appropriate acoustic and language model for the target language. Option D is correct because using the Speech SDK with intermediate results (via Recognizing events or continuous recognition) delivers real-time partial transcriptions as the caller speaks, which is required for live customer support transcription. Option E is correct because enabling the ProfanityFilter option (for example, setting Profanity to Masked or Removed in the SDK configuration) filters profane words from the recognized text. Option A is not appropriate because the Batch Transcription REST API is asynchronous and designed for processing stored audio files, not real-time streaming. Option B is unnecessary because custom speech models are only needed to improve accuracy for domain-specific vocabulary or accents, not merely to handle multiple languages, which built-in models already support.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use the Batch Transcription REST API
Why it's wrong here
Batch Transcription processes uploaded audio asynchronously, so it cannot deliver the real-time transcription the scenario demands. It is tempting because it handles multiple languages and profanity filtering, which suits transcribing archived call recordings rather than live support calls.
- ✗
Deploy a custom speech model for each language
Why it's wrong here
A single custom speech model per language cannot handle multiple languages simultaneously; custom models are trained on one locale's audio. It is tempting because custom models improve accuracy for specific vocabulary, which suits single-language deployments with domain-specific terminology.
- ✓
Set the SpeechConfig.SpeechRecognitionLanguage property
Why this is correct
Setting SpeechConfig.SpeechRecognitionLanguage specifies the spoken language the recogniser expects, satisfying the stem's multiple-language requirement. Without it, transcription defaults to en-US and misrecognises other languages. Note this property configures the source language only; profanity filtering is handled separately via ProfanityOption, so it is one of the three required settings.
- ✓
Use the Speech SDK with intermediate results
Why this is correct
Intermediate results stream partial transcriptions as the caller speaks, satisfying the real-time requirement that batch recognition cannot meet. Combined with auto language detection and profanity filtering, this SDK configuration delivers live multilingual transcription with masking.
- ✓
Enable the ProfanityFilter option in the Speech SDK
Why this is correct
Enabling the ProfanityFilter option in the Speech SDK masks or removes profane terms from recognised speech, directly satisfying the stem's requirement to filter profanity during real-time transcription. It operates on the recognition result independently of language handling, so it complements, rather than replaces, the multilingual configuration.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.