Text Normalization for Speech Quiz

Answers and explanations appear as you take the quiz.

1. What does text normalization for speech primarily do?
   • Rewrites written text into fully spoken-out words
   • Compresses audio files
   • Translates text into another language
   • Detects the speaker's emotion
2. How should a good system normalize '$5' for speech?
   • 'dollar five'
   • 'five dollars'
   • 'S five'
   • 'percent five'
3. Why is normalizing a token like 'Dr.' or 'IV' tricky?
   • These tokens are always pronounced the same way
   • They contain no letters
   • Their correct expansion depends on context
   • They are only used in math
4. What data did the cited neural text-normalization study use to evaluate its models?
   • Unlabeled phone audio only
   • Medical records annotated by clinicians
   • A small set of manually written code snippets
   • English and Russian Wikipedia sentences verbalized by Google TTS’s Kestrel system
5. What safeguard against unrecoverable errors does the cited neural text-normalization paper discuss?
   • WFST-based covering grammars
   • Removing the reference transcript
   • Replacing all token classes with a speech waveform
   • Using image segmentation at inference
6. In classic normalization, what is the role of assigning a token a 'semiotic class'?
   • It picks the speaker's voice
   • It labels the token (e.g., date, money, measure) so the right verbalizer is applied
   • It compresses the text
   • It removes all punctuation
7. In the Kestrel TTS normalization system, what follows tokenization and classification?
   • A speaker diarization pass labels voices
   • A vocoder renders the waveform
   • A verbalization stage applies grammars to turn classified tokens into spoken forms
   • An image model recognizes the page layout
8. Why can English and Russian text require different normalization grammars?
   • Every language uses identical number and date formats
   • Language has no effect on spoken forms
   • Russian text cannot be normalized for speech
   • Written conventions and verbalization rules vary by language