Kizspy | Question: 8 (Choose 1 answer)
A. A
B. B
C. C
D. D
Suppose you are building a speech recognition system, which uses an RNN model to map from audio clip & to a text transcript y. Your algorithm uses beam search to try to find the value of y that maximizes P(y x).
On a dev set example, given an input audio clip, your algorithm outputs the transcript ŷ = "I'm building an A Eye system in Silly con Valley.", whereas a human gives a much superior transcript y" = "I'm building an Al system in Silicon Valley."
According to your model,P(ŷ x) = 1.09*10-7 P(y*x) = 7.21 * 10-8
Would you expect increasing the beam width B to help correct this example?
a.No, because P(y* | x) ≤P(ŷ x) indicates the error should be attributed to the RNN rather than to the search algorithm.
b.No, because P(yx) ≤P(ŷ x) indicates the error should be attributed to the search algorithm rather than to the RNN.
C.Yes, because P(y* | x) ≤P(ŷ | x) indicates the error should be attributed to the RNN rather than to the search algorithm.
d.Yes, because P(y* | x) ≤P(ŷ | x) indicates the error should be attributed to the search algorithm rather than to the RNN.
