Speech AI Preferences Test
Preference test between speech synthesis modelsLoading...Mean
Comparison Graph
Mean table
Tag | model1_0410 | model2_1114 |
---|
Evaluation
CreatedType
Loading...Preference (Subjective preferences between the two audio)
Stimulus
CountRequested responsesLanguage
7410 per each audio (740 total)English (United States)
Evaluator
Total responsesValid/total evaluatorsGender ratio
74010 / 13 (77%)
MaleFemaleOther
37-
Custom evaluation query (2)
Question 1Listen to the speech/audio samples and rate which one you prefer overall?
Responses
5. B is strongly preferred4. B is preferred3. About the same2. A is preferred1. A is strongly preferred
Question 2Which audio do you prefer for American Accent?
Responses
5. B is strongly preferred4. B is preferred3. About the same2. A is preferred1. A is strongly preferred