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

More documents

Recommendations

Info

The following issues are addressed in this thesis: 1. Effect of wordboundary hypothesisation on lexical analysis, 2. Identification of language clues for word boundary hypothesisation, 3. Identification of lexical clues for word boundary hypothesisation, 4. Identification of prosodic clues for word boundary hypothesisation, and, 5. Identification of acoustic-phonetic clues for word boundary hypothesisation, 1.3 Studies on word boundary hypothesisation for Hindi The first study in our work is on the effect of word boundaries on lexical analysis. Experiments were carried out to compare the time spent on lexical matching for the two cases of word boundaries known and unknown. The results proved conclusively that the presence of word boundaries in the input sentences can reduce the time spent on lexical analysis significantly. For example, lexical analysis time for the sentence pa.-/Lsa.-la- me. erk mi- bplJd. ne.- pwc? l&a.- hai was reduced by a factor of 1000 when the word boundaries were known, compared to the case when the word boundaries were unknown, when the sentence had 10% errors in phonemes. Studies were also carried out to estimate the increase in the number of sentence alternatives for the input sentences. The studies showed that the presence of word boundaries, reduced the number of alternate word strings matching the input sentence. For example, for the sentence, pa.-ih~a=ln. me: e:k nni. Za+aki: ne:prave:s 1iya.- hoi produced nearly twice the number of alternate word strings when the word boundaries were unknown, compared to the case when the word boundaries were known, at an input error rate of 10%. Thus the results of the study established that word boundary hypothesisation improves the performance of the lexical analyser significantly. The next study relates to the identification of language clues for word boundary hypothesisation. The language clues proposed correspond to the frequently occurring
words. The idea is to spot symbol sequences corresponding to these frequently occurring words in the input sentences and hypothesise word boundaries around them. Depending on the frequency of occurrence of these words, one can hypothesise a large number of word boundaries. The above idea was tested on a Hindi text. A number of clues corresponding to the frequently occurring words such as case markers, pronouns and other function words were used. The results show that about 70% of the word boundaries were detected correctly with errors around 20%. However, in the context of speech recognition, the symbol string generated by the signal-to-symbol conversion contains errors. In our study, these errors were simulated in the input sentences and the performance of the language clues was estimated at various error rates. The results show that the language clues are useful for hypothesising word boundaries even at high error rates. For example, even at an input error rate of 50%, the language clues detected nearly 35% of the word boundaries with less than 35% incorrect hypotheses. The third study is on the identification of lexical clues. In this, lexical constraints such as the constraints on the sequences of phonemes, were proposed as clues to hypothesise word boundaries. The idea is to identify all phoneme sequences which do not occur word-internally, and then hypothesise word boundaries within such sequences occurring in a sentence. For example, in English, the phoneme sequence mgl does not occur word-internally. Hence if it is observed in a text (as in some glass), one can hypothesise a word boundary within the sequence. A number of phoneme sequences were used, ranging from simple sequences of vowels(v+) and cons on ants(^+) to much longer sequences of both vowels and consonants (CV'C and VC'V). Note that the superscript + is used to indicate a sequence of one or more symbols. Using these sequences, word boundaries were
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 and 14: alounddhelongtableheagsnoddedenunis
Page 15: word boundaries into a text with wo
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 ...

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?