Claims Analysis
Total Claims: 7
Claim 1
Independent Claim
190 words
A speech recognition system including Markov models which are adapted to be trained by an initial training label set and initial training speech using adaptation speech, and are used to recognise input speech, characterised in that said system comprises: means (5, 6, 7, 8, 9) for interpreting said adaptation speech into adaptation label strings using an adaptation label set: means for connecting each label in each of said adaptation label strings with each state or each state transition of a Markov model which corresponds to the adaptation label strings concerned; means for determining the confusion probability of each label in said initial training label set and each label in said adaptation label set being confused with each other, based on the connection between each label in said adaptation label set and each of said states or state transitions, and the parameter values of the Markov model concerned with said initial training set; and means for determining parameter values of each of said Markov models with respect to said adaptation label set, based on said confusion probabilities and said parameter values of the Markov model concerned with said initial label set.
Claim 2
Dependent Claim
190 words
A speech recognition system including Markov models which are adapted to be trained by an initial training label set and initial training speech using adaptation speech, and are used to recognise input speech, characterised in that said system comprises: means (5, 6, 7, 8, 9) for interpreting said adaptation speech into adaptation label strings using an adaptation label set: means for connecting each label in each of said adaptation label strings with each state or each state transition of a Markov model which corresponds to the adaptation label strings concerned; means for determining the confusion probability of each label in said initial training label set and each label in said adaptation label set being confused with each other, based on the connection between each label in said adaptation label set and each of said states or state transitions, and the parameter values of the Markov model concerned with said initial training set; and means for determining parameter values of each of said Markov models with respect to said adaptation label set, based on said confusion probabilities and said parameter values of the Markov model concerned with said initial label set.
Claim 3
Dependent Claim
26 words
A speech recognition system as claimed in Claim 1, characterised in that said adaptation label set is designed as different from said initial training label set.
Claim 4
Dependent Claim
46 words
A speech recognition system as claimed in Claim 2, characterised in that it comprises means for modifying a prototype of each label in said initial training label set using said adaptation speech so as to generate a prototype of each label in said adaptation label set.
Claim 5
Dependent Claim
56 words
A speech recognition system as claimed in Claim 3, characterised in that it comprises means for classifying feature vectors extracted from said adaptation speech into classes according to label prototypes of said initial training label set, and means for using an average of each of said classes as a corresponding prototype of said adaptation label set.
Claim 6
Dependent Claim
60 words
A speech recognition system as claimed in any one of the preceding claims, characterised in that said connection between each of said labels and each of said states or state transitions is established by an optimum path along which each of said adaptation label strings is aligned most favourably with a Markov model corresponding to the adaptation label string concerned.
Claim 7
Dependent Claim
61 words
A speech recognition system as claimed in any one of Claims 1, 2, 3 or 4, characterised in that said connection between each of said labels and each of said states or state transitions is established by a path by which each of said adaptation label strings is linearly aligned with a Markov model corresponding to the adaptation label string concerned.