word boundary- hypothesisation in hindi speech - Speech and ...

More documents

Recommendations

Info

oundaries, will also reduce the complexity in the processing of later stages, such as lekcal, syntactic and semantic analyses. 1.2 Issues in word boundary hypothesisation In the previous section, it was argued that word boundaries can reduce the number of alternatives produced by a lexical analyser, and they can also reduce the computation involved in lexical analysis. However, one can also obtain a quantitative assessment of the effect of word boundaries on lexical analysis and thereby establish the importance of the word boundary hypothesisation in lexical analysis. This is the first task in our work. The main issue to be addressed in such a study is the improvement in the performance of the lexical analyser due to word boundary hypothesisation. This involves two studies: (1) a study of the effect of errors in the input symbols on the performance of the lexical analyser when the input sentences contain no word boundaries, and (2) a study on the performance of the lexical analyser for the same input sentences when they contain word boundaries. In these studies, the performance of the lexical analyser is measured using two terms: (i) the number of alternate word strings (henceforth referred as alternatives) matching the input sentence, and (ii) the time spent on the lexical analysis. These meas-dres reflect the different ways in which lexical analysis influences the overall speech recognition process. The first measure is an estimate of the computational load imposed on the later stages of processing, such as syntactic and semantic analyses, whereas the second measure is an estimate of the computation involved in the lexical analysis. Once the importance of the word boundary hypothesisation is established, the next task is to identify some clues to perform word boundary hypothesisation. Since word boundary hypothesisation can be viewed as converting a string of symbols without
word boundaries into a text with word boundaries, one can exploit some language features to perform this task. In particular, one can utilise the constraints on the formation of words and their occurrence within a sentence. Thus the lexical and higher level linguistic knowledge scurces such as synta and semantics, which wili be referred henceforth as language knowledge, are needed to identify the clues for word boundary hypothesisation. In this context, we have identified two studies, one on the use of language clues to perform word boundary hypothesisation and another on the use of lexical clues. In the context of speech recognition, the symbol string produced by the speech signal-to-symbol converter, usually contains errors. It is possible that in the presence of errors, the lexical and the language clues may not be as effective as in the case of error free input. But there are several speech related knowledge sources such as prosody and acoustic-phonetics which can be examined to identify additional clues. Thus we have identified additional studies on the identification of prosodic and acoustic-phonetic clues for word boundary hypothesisation. From the above discussion, it is clear that clues based on the four knowledge sources, acoustic-phonetic, prosodic, lexical and language are useful for word boundary hypothesisation. However, it may not be possible to integrate all of these clues into a single module. This is due to the fact that the acoustic-phonetic and prosodic clues can be applied on the speech signal only, whereas the lexical and language clues are applicable on the symbol string output by the speech signal-to-symbol converter. Hence to perform word boundary hypothesisation, one needs to obtain the various clues from the appropriate knowledge sources and use them, rather than build a single module for word boundary hypothesisation. The present work focuses on the identification of clues to perform word boundary hypothesisation, and no attempt is made to address issues concerned with the application of these clues in an integrated fashion.
Page 1 and 2: Dr. €3. YEGNANARAYANA Professor D
Page 3 and 4: ACKNOWLEDGEMENTS I thank my researc
Page 5 and 6: -3 SIGNIFICANCE OF WORD BOUNDARIES
Page 7 and 8: 6.6 Location of word boundaries fro
Page 9 and 10: ABSTRACT This thesis addresses the
Page 11 and 12: \ known. The lexical analyser can n
Page 13: alounddhelongtableheagsnoddedenunis
Page 17 and 18: words. The idea is to spot symbol s
Page 19 and 20: F1 position at a vowel-consonant bo
Page 21 and 22: -a2 A REVIEW OF THE STUDIES ON, WOR
Page 23 and 24: 1. When a midclass representation w
Page 25 and 26: particular interest is the performa
Page 27 and 28: was found that at broadclass level,
Page 29 and 30: in speaking rate indicate phrase bo
Page 31 and 32: y an estimator function E from the
Page 33 and 34: studies, the following issues are i
Page 35 and 36: 2. The effect of word boundary info
Page 37: * This selection can be done in man
Page 40 and 41: me : me:ra: metra: na: me:ra: na:m
Page 42 and 43: No. of alternatives 0-10 10-100 100
Page 44 and 45: 3.3.2 Results of lexical analysk wi
Page 46 and 47: had to be restricted to the above r
Page 48 and 49: Match Sentence nunber cost 1 2 3 4
Page 50 and 51: Match Sentence nuher cost 1 2 3 4 5
Page 52 and 53: 6 10 Number of 10 a1 ternate word s
Page 54 and 55: lexlcal analysis Mismatch cost Fig.
Page 56 and 57: had all word boundaries, is plotted
Page 58 and 59: Watch Sentence number cost 1 2 3 4
Page 60 and 61: Time lor lexical analysis 0 1 2 3 4
Page 62 and 63: Match Sentence tunter cost 1 2 3 4
Page 64 and 65:
Time lor lexical analysis 1 0 1 2 3
Page 66 and 67:
speech recognition process. On the
Page 68 and 69:
proposed clues are based on the obs
Page 70 and 71:
Case Markers: Pronouns : ka:, ki:,
Page 72 and 73:
form. The above Hindi text was corr
Page 74 and 75:
that if there are some substitution
Page 76 and 77:
These measures were defined as foll
Page 78 and 79:
Case Conjunc- Pronouns Verb Aux . A
Page 80 and 81:
- I-' X Error in input text X Error
Page 82 and 83:
% Error Fig.4.4 Results of word bou
Page 84 and 85:
% Error Fig.4.5 A comparison of the
Page 86 and 87:
0 I 1 I 0 10 20 30 40 50 60 % Error
Page 88 and 89:
60 4 0 No. of subsentences No. of s
Page 90 and 91:
LC1: A Hindi word can end either in
Page 92 and 93:
Fig.4.10 along with the results for
Page 94 and 95:
oundaries spotted) against system s
Page 96 and 97:
from other words, such as 'national
Page 98 and 99:
dictionary contained nearly 30000 w
Page 100 and 101:
Vowel sequences Consonant sequences
Page 102 and 103:
VC' were considered. It can be obse
Page 104 and 105:
percentage of incorrect hypotheses
Page 106 and 107:
% Error in input text 0 10 20 30 40
Page 108 and 109:
% Error Fig.5.1 Results of word bou
Page 110 and 111:
hypotheses produced by the lexical
Page 112 and 113:
transformed into other nonword-inte
Page 114 and 115:
WB hyp. errors 300 - 200 - ( v+> 10
Page 116 and 117:
number of incorrect hypotheses will
Page 118 and 119:
I--- Correctness 60 8o lmprovement
Page 120 and 121:
% Error in input text 10 20 30 40 5
Page 122 and 123:
will be smaller and hence S and P(y
Page 124 and 125:
word boundary is within the consona
Page 126 and 127:
clues except for clues of types CV'
Page 128 and 129:
Pauses in speech, though small in n
Page 130 and 131:
Several studies on English speech s
Page 132 and 133:
Speaker VB hypotheses at various th
Page 134 and 135:
Speaker UF hypotheses at various th
Page 136 and 137:
Speaker UF hypotheses at various th
Page 138 and 139:
Fig.6.1 The plot of pitch frequency
Page 140 and 141:
From the results, it can be seen th
Page 142 and 143:
speakers, with the incorrect hypoth
Page 144 and 145:
durational effects. One possible ex
Page 146 and 147:
From these results, it can be seen
Page 148 and 149:
shown that the prosodic features of
Page 150 and 151:
chapter 7 WORD BOUNDARY CLUES BASED
Page 152 and 153:
consonants. Thus one can consider o
Page 154 and 155:
Speaker VB hypotheses(VB:&) at vari
Page 156 and 157:
Speaker UF hypotheses(UF:UI) at var
Page 158:
Speaker UB hypotheses(UB:B) at vari
Page 161 and 162:
high speaking rates. This is also b
Page 163 and 164:
vowels preceding word boundaries, i
Page 165 and 166:
word-final vowels than word-interna
Page 167 and 168:
8.1 Introduction PERFORMANCE OF WOR
Page 169 and 170:
Match Sentence nunber, cost 1 2 3 4
Page 171 and 172:
75 Reduction in the time for lexica
Page 173 and 174:
The reduction in the lexical analys
Page 175 and 176:
Hatch Sentence nuher cost 1 2 3 4 5
Page 177 and 178:
Chapter 9 SUMMARY AND CONCLUSIONS I
Page 179 and 180:
In the last study (described in cha
Page 181 and 182:
the language and lexical clues are
Page 183 and 184:
REFERENCES Baken R.J. and Daniloff
Page 185 and 186:
Cutler A. and Butterfield S. (199lb
Page 187 and 188:
Prakash M., Ramana Rao G,V., Chandr
Page 189 and 190:
Zelenski R. and Class F. (1983), A
show all

word boundary- hypothesisation in hindi speech - Speech and ...

Create successful ePaper yourself

Delete template?

Save as template?