Why does inconsistent accent placement within machine-generated speech risk a decline in perceived user satisfaction from a voice assistant?

💡 Explanation

Inconsistent accent breaks the user's learned rhythmic expectancy patterns, which causes the speech to sound unnatural and difficult to process. Therefore, satisfaction decreases because the cognitive load increases, rather than the issues being due to computational load or language model errors.

• Within Mandarin Chinese, why do some instances of tone sandhi unexpectedly fail to apply at a prosodic domain boundary?
• If a language undergoes significant grammaticalization, which consequence follows for lexical items used as grammatical markers?
• In a multi-turn spoken dialogue system managing a user's itinerary, which consequence follows if the system incorrectly marks a previously 'new' detail as 'given'?
• Why does a 'euphemism treadmill' often lead to the original taboo term becoming re-stigmatized within sociolinguistics?
• Why does unequal character spacing in optically-scaled fonts reduce user reading comprehension more than mechanically-scaled?
• A statistical machine translation system, optimized for low-resource languages, uses a neural attention mechanism. If the training data contains substantial code-switched sentences, which outcome is most likely?