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）︰2004.05.18
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 18 2004 10:10 a.m. ~ 12:10 p.m.
● OPEN EVERYTHING
● 除專有名詞可用英文外，所有文字說明一律以中文為限，未用中文者不計分。
● Total points: 120, Time allocation: 1 point / 1 minute
───────────────────────────────────────
1. (15) Describe the basic elements, operations and relevant research issues
of spoken dialogue systems.
2. (10)
(a) (5) What are voiced/unvoiced speech signals and their time domain
waveform characteristics?
(b) (5) What is the pitch in speech signals and how is it related to the
tones in Mandarin Chinese?
╴
3. (20) Given a HMM λ = (A, B, π), an observation sequence Ｏ = 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) Show that prob(Ｏ│λ) = Σ [α_t(i) β_t(i)].
i=1
╴ α_t(i) β_t(i)
(b) (5) Show that prob[q_t = i│Ｏ, λ] = ───────────
N
Σ [α_t(i) β_t(i)]
i=1
(c) (10) Formulate and describe the procedures for Viterbi Algorithm to find
the best state sequence q*(上面加底線) = q_1* q_2* ... q_t* ... q_T*.
4. (10) Explain what the segmental k-means algorithm is and how it works.
5. (10) Explain: in designing the decision tree to train tri-phone models, how
the information theory is used to split a node n into two nodes a and b.
6. (12) The perplexity of a language source S is
H(S)
PP(S) = 2 , H(S) = -Σ p(x_i) log[p(x_i)],
i
where x_i is a word in the language, Explain why PP(S) is the estimate of
the branching factor for the language assuming a "virtual vocabulary"?
7. (8) Explain what the class-based language model is and why it is useful.
8. (15) For large vocabulary continuous speech recognition, explain how the
Viterbi algorithm can be performed over a lexicon tree of phone unit HMMs
such that the knowledge from the acoustic models, lexicon nad language
model can be efficiently integrated?
9. (20) Write down anything you learned about the following subjects which
were NOT mentioned in class. Don't write down anything mentioned in the
class.
(a) (10) speech signals or acoustic modeling
(b) (10) language model analysis or smoothing