中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

30 records (took 0.02 seconds)

    21.
    发明专利
    未知

    公开(公告)号：DE3680903D1

    公开(公告)日：1991-09-19

    申请号：DE3680903

    申请日：1986-03-27

    Applicant: IBM

    Inventor： BAHL LALIT RAI ,  DESOUZA PETER VINCENT ,  MERCER ROBERT LEROY ,  PICHENY MICHAEL ALAN

    IPC: G10L15/04 ,  G10L5/06

    Abstract: The speech processing method is applied to a speech recognition system having an acoustic processor for processing multiple utterances of a word in the construction of a fenemic baseform for the word. The method involves providing as input a string of fenemes generated by the acoustic processor in response to an utterance of the word. This is repeated for each utterance of the multiple utterances. A consistent print in each input string of fenemes is located where each string of fenemes is divided by the consistent point into a left portion and a right portion. The left portions of all the input strings of fenemes represent a common sequence of sounds, and the right portions a common sequence of sounds.

    26.
    发明专利
    未知

    公开(公告)号：DE3874049D1

    公开(公告)日：1992-10-01

    申请号：DE3874049

    申请日：1988-06-16

    Applicant: IBM

    Inventor： BAHL LALIT RAI ,  MERCER ROBERT LEROY ,  NAHAMOO DAVID

    IPC: G10L11/00 ,  G10L15/06 ,  G10L15/14 ,  G10L5/06

    Abstract: Apparatus and method for training the statistics of a Markov Model speech recognizer to a subsequent speaker who utters part of a training text after the recognizer has been trained for the statistics of a reference speaker who utters a full training text. Where labels generated by an acoustic processor in response to uttered speech serve as outputs for Markov models, the present apparatus and method determine label output probabilities at transitions in the Markov models corresponding to the subsequent speaker where there is sparse training data. Specifically, label output probabilities for the subsequent speaker are re-parameterized based on confusion matrix entries having values indicative of the similarity between an l th label output of the subsequent speaker and a kth label output for the reference speaker. The label output probabilities based on re-parameterized data are combined with initialized label output probabilities to form "smoothed" label output probabilities which feature smoothed probability distributions. Based on label outputs generated when the subsequent speaker utters the shortened training text, "basic" label output probabilities computed by conventional methodology are linearly averaged against the smoothed label output probabilities to produce improved label output probabilities.

    27.
    发明专利
    未知

    公开(公告)号：DE3779170D1

    公开(公告)日：1992-06-25

    申请号：DE3779170

    申请日：1987-03-24

    Applicant: IBM

    Inventor： BAHL LALIT RAI ,  DESOUZA PETER VINCENT ,  MERCER ROBERT LEROY ,  PICHENY MICHAEL ALAN

    IPC: G10L11/00 ,  G10L15/06 ,  G10L15/14 ,  G10L5/06

    Abstract: Apparatus and method for synthesizing word baseforms for words not spoken during a training session, wherein each synthesized baseform represents a series of models from a first set of models, which include: (a) uttering speech during a training session and representing the uttered speech as a sequence of models from a second set of models; (b) for each of at least some of the second set models spoken in a given phonetic model context during the training session, storing a respective string of first set models; and (c) constructing a word baseform of first set models for a word not spoken during the training session, including the step of representing each piece of a word that corresponds to a second set model in a given context by the stored respective string, if any, corresponding thereto.

    28.
    发明专利
    未知

    公开(公告)号：DE3680904D1

    公开(公告)日：1991-09-19

    申请号：DE3680904

    申请日：1986-03-27

    Applicant: IBM

    Inventor： BAHL LALIT RAI ,  DESOUZA PETER VINCENT ,  MERCER ROBERT LEROY ,  PICHENY MICHAEL ALAN

    IPC: G10L15/04 ,  G10L5/06

    Abstract: The method involves forming a set of phonetic phone machines. Each phone machine has (i) several states, (ii) several transitions each of which extends from state to state, (iii) a stored probability for each transition, and (iv) stored label output probabilities.Each label output probability corresponds to the probability of each phone machine producing a corresponding label. The set of phonetic machines is formed to include a subset of onset phone machines, the stored probabilities of each onset phone machine corresponding to a phonetic element being uttered at the beginning of a speech segment. Word baseforms are constructed by concatenating phone machines selected from the set.

    29.
    发明专利
    未知

    公开(公告)号：DE3670166D1

    公开(公告)日：1990-05-10

    申请号：DE3670166

    申请日：1986-01-28

    Applicant: IBM

    Inventor： BAHL LALIT RAI ,  DESOUZA PETER VINCENT ,  MERCER ROBERT LEROY

    IPC: G10L11/00 ,  G10L15/02 ,  G10L15/14 ,  G10L5/06

    Abstract: For improving the efficiency of a speech recognition system based on a vocabulary of statistical word models, initially coarse word preselections are made for utterances, and are marked in a training session to indicate whether the selections were correct or wrong. Furthermore, each utterance is matched against each word preselected for it to obtain a probability measure for that combination as in a usual reccgnition process. Based on this knowledge of the correct or erroneous result of the coarse selection plus the probability measure, a discriminant analysis is made to determine, for the whole population of word models, how each phone in each word model should be weighted so that an optimum discrimination between similar words is achieved. The weighting coefficients thus obtained are stored with the word models and are later used, during actual speech recognition, to weight the probabilistic contribution of each phone for the final word selection.

Patent Agency Ranking