27
(Choose 1 answer)
Suppose you are building a speech recognition system, which uses an RNN model to map from audio clip 2 to a text transcript y. Your algorithm uses beam search to try to find the value of y that maximizes P(yx).
On a dev set example, given an input audio clip, your algorithm outputs the transcript y = "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(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( x) indicates the error should be attributed to the RNN rather than to the search algorithm.
b.No, because P(y x) ≤P(x) indicates the error should be attributed to the search algorithm rather than to the RNN.
C.Yes, because P(y x) ≤P(yz) indicates the error should be attributed to the RNN rather than to the search algorithm.
d. Yes, because P(y+x) ≤P(x) indicates the error should be attributed to the search algorithm rather than to the RNN.
A. B
B. D
C. C
D. A
