a$)$ Consider that you have to design the application of $$Speech to Text Conversion$.$ Assuming that the input

can be noisy, suggest a method to correct the noise using probability distribution $($or probability

knowledge$).$ Support your answer using mathematical formulations and assumptions wherever possible.

Limit your answer to the topics studied during the course.

b$)$ The following list of R$$s and N$$s represents relevant $($R$)$ and non$-$relevant $($N$)$ returned documents in a

ranked list of $20$ documents retrieved in response to a query from a collection of $10,000$ documents. The

top of the ranked list $($the document the system thinks is most likely to be relevant$)$ is given below. This list

shows $6$ relevant documents, and rest non$-$relevant. Assume that there are $8$ relevant documents in total

in the collection. What is the precision and recall of the system on the top $20?$

R R N N N N N N R N R N N N R N N N N R