課程名稱︰數位語音處理概論 課程性質︰選修 課程教師︰李琳山 開課學院：電資學院 開課系所︰電機、資工系 考試日期（年月日）︰2007.05.15 考試時限（分鐘）：120 是否需發放獎勵金：是 （如未明確表示，則不予發放） 試題 : Digital Speech Processing, Midterm May. 15, 2007, 9:10-11:10 ● OPEN EVERYTHING ● 除專有名詞可用英文以外，所有文字說明一律以中文為限，未用中文者不計分 ● Total points: 170 ─────────────────────────────────────── 1. (10) Describe what you know about the basic elements, operations and relevant research issues of conversational interfaces or spoken dialogue systems. ╴ t 2. (10) Assume Ｘ = (x1, x2) is a two-dimensional random vector with t bi-variate Gaussian distribution, a mean vector μ(上面加底線) = (μ1, μ2) and a co-variance matrix Σ. x1, x2 are two random variables and "t" means transpose. Discuss how the distribution of Ｘ(上面加底線) depends on μ(上面加底線) and Σ. 3. (20) Given a HMM λ = (A, B, π) with N states, an observation sequence Ｏ(上面加底線) = o_1 o_2 ... o_t ... o_T and a state sequence q(上面加底線) = q_1 q_2 ... q_t ... q_T, define α_t(i) = Prob[o_1 o_2 ... o_t, q_t = i│λ] β_t(i) = Prob[o_(t+1) o_(t+2) ... o_T│q_t = i, λ] N (a) (5) What is Σ α_t(i) β_t(i) ? Show your results. i=1 α_t(i) β_t(i) (b) (5) What is ─────────── ? Show your results. N Σ [α_t(i) β_t(i)] i=1 (c) (5) What is α_t(i) a_ij b_j(o_(t+1)) β_(t+1)(j)? Show your results. (d) (10) Formulate and describe the Viterbi algorithm to find the best state sequence q*(上面加底線) = q_1* q_2* ... q_t* ... q_T* giving the highest probability Prob[Ｏ(上面加底線), q*(上面加底線)│λ]. Explain how it works and why backtracking is necessary. 4. (10) What is LBG algorithm and why is it better than K-means algorithm? 5. (10) Explain why and how the unseen triphones can be trained using decision trees. 6. (10) In acoustic modeling the concept of "senones" is very useful. Explain what is a "senone" and how it can be used. 7. (10) Explain the basic principles in selecting the voice units for a language for hidden Markov modeling. 8. (10) Explain what the class-based language model is and why it is useful? 9. (10) What is the perplexity of a language source? What is the perplexity of a language model with respect to a corpus? How are they related to a "virtual vocabulary"? 10. (10) Explain why the use of a window with finite length, w(n), n = 0, 1, 2, ... , L-1, is necessary for feature extraction in speech recognition. 11. (10) In feature extraction for speech recognition, after you obtain 12 MFCC parameters plus a short-time energy (a total of 13 parameters), explain how to obtain the other 26 parameters and what they are. 12. (10) In large vocabulary continuous speech recognition, explain: (a) (5) What the "language model weight" is. (b) (5) Why the language model has the function as the penalty of inserting extra words. 13. (20) What is the maximum a posteriori (MAP) principle? How can it be used to integrate acoustic modeling and language modeling for large vocabulary speech recognition? Why and how this can be solved by a Viterbi algorithm over a series of lexicon trees? 14. (15) Under what kind of condition a heuristic search is admissible? Show or explain why? --

※ 發信站: 批踢踢實業坊(ptt.cc), 來自: 114.45.19.183 ※ 文章網址: http://webptt.com/m.aspx?n=bbs/NTU-Exam/M.1398086394.A.1F8.html