[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Speech quality test with unmatched language?
I'm curious how much language information affects the result of a subjective speech quality test.
Does anybody know of works on subjective speech quality tests (e.g., MOS test) with "unmatched language condition", where subjects have to decide the quality of unknown language? For example, native German subjects can be presented with American Indian language. How much would the result be different when subjects are replaced with American Indians?