?????????????? - PowerPoint PPT Presentation

1 / 22
About This Presentation
Title:

??????????????

Description:

Title: PowerPoint Author: H.C.Wang Last modified by: admin Created Date: 12/12/2001 8:26:32 AM Document presentation format: (4:3) – PowerPoint PPT presentation

Number of Views:37
Avg rating:3.0/5.0
Slides: 23
Provided by: HC96
Category:
Tags: decision | markov

less

Transcript and Presenter's Notes

Title: ??????????????


1
????????
????? ?????????????? ???? A Study on the Next
Generation Automatic Speech Recognition -- Phase
2
??? ??? 2011//7/12
2
??????????
??????????
3
??????(automatic speech recognition,
ASR)?????????????,??????????????????????,?????????
??,???????????????????,??????????????,????????????
???????????????(hidden Markov model)???????(artifi
cial neural network),??????,???????????????????? ?
???????(corpus-based)??,???????????????(knowledge-
ignorant modeling),????????? ??????????????????,?
?????????(knowledge-based)??????(data-driven)???,?
?????????????,????????????????
4
???????????????????,???2005???????????????????????
???,??????,??????,??????????
??????????????,?????????????????,????????????
5
2008????????????????????????????-?????,???????????
,?????????????????
6
?????????
?????????
7
??????????????,?????????????????????,?????????????
?????????????,?????????,???????
8
???????????? (???) --- ????(?)
?????????????? (1)???????? (2)????????? (3)????(A
udio Segmentation)????? (4)??????(Automatic
Phoneme Segmentation)????? (5)????????(Feature
Selection)????? (6)?????????????
9
?????????????? (???) --- ????(?)
???????????????,??????????????????,???????????????
??? (1) ????????????? (2) ??????????????????????
(3) ???????????????????? (4) ?????????????????????
???
10
???????????,???? (???) --- ????(?)?????(?)
??????????????(?)?????(?)? ????(?)??????? (1)????
??????????????????? (2)???????????????????????????
? (3)????????????????????????????? ????(?)???????
?????(Viterbi Decoding)???,????????,??????????(Hid
den Markov Model)?????(Graphical
Model)??????(Conditional Random
Field)??????(Maximum Entropy Model)????(Decision
Tree)??????(Support Vector Machine)??
11
?????????????? (???) --- ????(?)?????(?)
???????????????????????,????????????,????????????,
?????????? ???????????? (1)??????????,???????????
??? (2)????????????????????????????????? (3)?????
????????????????????????
12
???????????????????? (???) --- ????(?)
???????????? (1) ?HMM????????????? (2)
??????(syllable boundary landmark)???? (3)
???????????? (4) ???????????????????
13
??????????????????? (???) --- ????(?))
????????????(?),???????,??,????????,???????local
time-frequency cues,??????locus,contrast?supra-seg
ment??,??????time-frequency cues,?????????????????
?????,??????environment-invariant
features??????????????????? ?????? (1)
?????????????? (2) ??????????? (3)
?????????????,Universal phone detector?Robust
word detector ? (4) ??(Offline)???(real-time)????
14
?????????
???????????????????????????????,?????????? (1)
???????? (2) ???????? (3) ?????????? (4)
???????? http//diana.ee.nthu.edu.tw/NGASR/
15
????????????
???????
16
????(?) ???????????? (???) ?????????????(???) ????
????????(???) ??????????????(???)
17
????(?) ??????(conditional random
field)????????????(???) ?????(random
forest)??????????(???) ??????(voice onset
time)???(???) ????Gabor Feature???????????????(???
)
18
????(?) ????????????(???) ?HMM????????????????????
??(???) ???????(Toolkit)????(???) ????????(Course
Lecture Corpus)????(???) TCC300???????????(???)
19
????(?) ???????(Hierarchical Structure)??????(???)
??Gabor Feature?MFCC,??????????(MLP)???????(Tande
m System),?????????(???)
20
????(?) ????????????????????(???) ??????(discourse
Prosody Context)????(???) ?????????(NTU Lecture
corpus)???????(???) ??????????????????????????????
(???)
21
?????
22
Automatic Phone Alignment and Recognition Detectio
n of Burst Onset Using Random Forest Technique
and Its Application to Voice Onset Time
Estimation Speech Recognition Integrating Gabor
Features with a Hierarchical structure Discourse
Prosodic Attributes, Boundary Information and
Prosodic Highlight High-Resolution Phone Boundary
Detection Using Sample-Based Acoustic
Parameters ??????????????????????
Write a Comment
User Comments (0)
About PowerShow.com