Patents Examined by Susan Wieland
  • Patent number: 6052664
    Abstract: The present invention describes an apparatus and method for generating phonetico-prosodic parameters of a predetermined message starting from a source message. The predetermined message comprises carriers and phrases. The phonetico-prosodic parameters of the carriers and the phrases are stored in a memory after having been generated off-line. The invention also comprises an apparatus and method for electronically generating a spoken message starting from phonetico-prosodic parameters, stored in said memory. The carriers comprise fixed parts and open slots filled with arguments. The phonetico-prosodic parameters of the arguments to be filled in in the open slots are generated at run time.
    Type: Grant
    Filed: December 15, 1997
    Date of Patent: April 18, 2000
    Assignee: Lernout & Hauspie Speech Products N.V.
    Inventors: Bert Van Coile, Stefaan Willems, Steven Leys
  • Patent number: 6049770
    Abstract: A video and voice signal processing apparatus is provided. The apparatus includes a signal receiving circuit for receiving an input signal containing a plurality of frames, each frame having an encoded voice signal block and an encoded video signal block. The signal receiving circuit separates the encoded voice signal block from the encoded video signal block in each frame. A voice signal processor converts the encoded voice signal block into a voice signal. Also included is a video extracting circuit which decimates a plurality of encoded video signal blocks and extracts one of the encoded video signal blocks as a representative video signal. A video signal processor converts the representative video signal into a video signal.
    Type: Grant
    Filed: May 29, 1998
    Date of Patent: April 11, 2000
    Assignee: Matsushita Electric Industrial Co., Ltd.
    Inventors: Junji Yoshida, Akira Iketani, Chiyoko Matsumi, Tatsuro Juri
  • Patent number: 6049767
    Abstract: A method and apparatus for efficiently determining the gain of a feature function in a maximum entropy/minimum divergence probability model in a single pass through a training corpus. A method for determining the gain of a feature in such a model includes the steps of a selecting a set of evaluation points and determining the value of a function referred to as the gainsum derivative at each of the evaluation points. An approximation function which can be evaluated at substantially any point in a continuous domain is then selected based upon the discrete values of the gainsum derivative at the evaluation points. The approximation function is then employed to determine the argument value that maximizes an approximated gain function. The approximate gain value is then determined by evaluating the approximated gain function at this argument value. The apparatus of the present invention includes means for performing the steps of the disclosed method.
    Type: Grant
    Filed: April 30, 1998
    Date of Patent: April 11, 2000
    Assignee: International Business Machines Corporation
    Inventor: Harry W. Printz
  • Patent number: 6044340
    Abstract: A method and apparatus for removing convolution noise from a signal such a one carrying speech information. The signal is transformed into a log-spectral domain where a smoothed model is fitted to the log-spectrum subject to constraints of concavity and an overall bandpass shape. The smoothed model has quadratic segments of negative curvature and linear segments, the segments being smoothly joined at breakpoints. The model, which may be recursively updated, is subtracted from each log-spectral data vector.
    Type: Grant
    Filed: February 13, 1998
    Date of Patent: March 28, 2000
    Assignee: Lernout & Hauspie Speech Products N.V.
    Inventor: Hugo Van Hamme
  • Patent number: 6029125
    Abstract: Sparseness is reduced in an input digital signal which includes a first sequence of sample values. An output digital signal is produced in response to the input digital signal. The output digital signal includes a second sequence of sample values, which second sequence of sample values has a greater density of non-zero sample values than the first sequence of sample values.
    Type: Grant
    Filed: July 7, 1998
    Date of Patent: February 22, 2000
    Assignee: Telefonaktiebolaget L M Ericsson, (publ)
    Inventors: Roar Hagen, Bjorn Stig Erik Johansson, Erik Ekudden, Willem Baastian Kleijn
  • Patent number: 6029136
    Abstract: A coding process having a band dividing filter and a decoding process having a subband synthesizing filter are arranged so that the operating accuracy is enhanced only in a specific subband, for securing the necessary sound quality with a relatively small amount of the operation. A band dividing control unit is served to derive a signal level of each subband from the output result of a fast band dividing filter and generate a high-accurate operation band specifying command for specifying a subband of a low signal level. A high-accuracy band dividing filter is executed to perform a band dividing operation for the subband of the low signal level specified by the high-accuracy band specifying command.
    Type: Grant
    Filed: November 7, 1996
    Date of Patent: February 22, 2000
    Assignee: Sony Corporation
    Inventor: Kyoya Tsutsui
  • Patent number: 6029124
    Abstract: A speech sample is evaluated using a computer. Training data that include samples of speech are received and stored along with identification of speech elements to which portions of the training data are related. A speech sample is received and speech recognition is performed on the speech sample to produce recognition results. Finally, the recognition results are evaluated in view of the training data and the identification of the speech elements to which the portions of the training data are related. The technique may be used to perform tasks such as speech recognition, speaker identification, and language identification.
    Type: Grant
    Filed: March 31, 1998
    Date of Patent: February 22, 2000
    Assignee: Dragon Systems, Inc.
    Inventors: Laurence S. Gillick, Andres Corrada-Emmanuel, Michael J. Newman, Barbara R. Peskin
  • Patent number: 6014618
    Abstract: A method and apparatus for reducing the complexity of linear prediction analysis-by-synthesis (LPAS) speech coders. The method and apparatus include product code vector quantization (PCVQ) of multi-tap pitch predictor coefficients, which reduces the search and quantization complexity of an adaptive codebook. Further included is a procedure for generating and selecting code vectors consisting of ternary (1,0,-1) values, for optimizing a fixed codebook. Serial optimization of the adaptive codebook first and then the fixed codebook, produces a low complexity LPAS speech coder of the present invention.
    Type: Grant
    Filed: August 6, 1998
    Date of Patent: January 11, 2000
    Assignee: DSP Software Engineering, Inc.
    Inventors: Jayesh S. Patel, Douglas E. Kolb
  • Patent number: 6014623
    Abstract: A method of synthetic speech, wherein the method forms a speech data base, the speech data base includes plural syllables, each of the syllables having a total frame number of the syllable and plural frame parameters. Each of the frame parameter is formed using an energy amount, a speech pitch period, and 10 Line Spectrum Pair (LSP) speech parameters. Thereafter, each LSP speech parameter is encoded using 4 bit Differential Quantization.
    Type: Grant
    Filed: June 12, 1997
    Date of Patent: January 11, 2000
    Assignee: United Microelectronics Corp.
    Inventors: Xingjun Wu, Yihe Sun
  • Patent number: 6012026
    Abstract: A transmission system with a transmitter and a receiver. The transmitter has a speech encoder with analysis means, has calculation means, and has control means. The receiver has a speech decoder. Through a transmission medium, the transmitter transmits frames of data to the receiver. The analysis means determine analysis coefficients from a speech signal. From a bitrate setting, the calculation means calculate a fraction of the frames of data to carry more information about the analysis coefficients than a remaining number of the frames of data. The control means control the transmitter to transmit the fraction of the frames of data and to transmit the remaining number of the frames of data. The receiver receives the frames of data. The receiver derives a reconstructed speech signal from the received frames of data.
    Type: Grant
    Filed: March 31, 1998
    Date of Patent: January 4, 2000
    Assignee: U.S. Philips Corporation
    Inventors: Rakesh Taori, Andreas J. Gerrits
  • Patent number: 6009395
    Abstract: A synthesizer may synthesize speech by receiving an adaptive codebook excitation signal and an adaptive codebook gain. The adaptive codebook excitation signal may be scaled using the adaptive codebook gain to generate a scaled adaptive codebook excitation signal. A fixed excitation signal and a fixed excitation gain may also be received. The fixed excitation signal may be scaled using the fixed excitation gain to generate a scaled fixed excitation signal. The scaled adaptive codebook excitation signal and the scaled fixed excitation signal may be combined to generate the excitation signal having a first word length. An overall gain signal of the excitation signal may also be received. A scaled excitation signal may then be generated by scaling the excitation signal using the overall gain signal. The scaled excitation signal may have a second word length greater than the first word length.
    Type: Grant
    Filed: December 29, 1997
    Date of Patent: December 28, 1999
    Assignee: Texas Instruments Incorporated
    Inventors: Wai-Ming Lai, Alan V. McCree, Erdal Paksoy
  • Patent number: 6009384
    Abstract: For coding human speech for subsequent audio reproduction thereof, a plurality of speech segments is derived from speech received, and systematically stored in a data base for later concatenated readout. After the deriving, respective speech segments are fragmented into temporally consecutive source frames, similar source frames as governed by a predetermined similarity measure thereamongst that is based on an underlying parameter set are joined, and joined source frames are collectively mapped onto a single storage frame. Respective segments are stored as containing sequenced referrals to storage frames for therefrom reconstituting the segment in question.
    Type: Grant
    Filed: May 20, 1997
    Date of Patent: December 28, 1999
    Assignee: U.S. Philips Corporation
    Inventors: Raymond N. J. Veldhuis, Paul A. P. Kaufholz
  • Patent number: 6006176
    Abstract: A speech coding apparatus which allows a speech decoding apparatus to output a more familiar background noise. The speech coding apparatus includes a voice presence/absence discrimination section, a coding section, a unique word production section, and a data switching section which selectively outputs one of outputs of the coding section and the unique word production section as an output of the speech coding apparatus in response to a result of discrimination of the voice presence/absence discrimination section. The speech coding apparatus further includes an amplitude level discrimination section, a clip processing section and an input switching section. The input switching section selects, when the input speech signal includes voice, the input speech signal, but when the input speech signal includes no voice and a code for updating background noise is to be produced, the input switching section selects the input speech signal after clip processing.
    Type: Grant
    Filed: June 26, 1998
    Date of Patent: December 21, 1999
    Assignee: NEC Corporation
    Inventor: Toshihiro Hayata
  • Patent number: 6006182
    Abstract: Systems and methods consistent with the present invention determine whether to accept one of a plurality of intermediate recognition results output by a speech recognition system as a final recognition result. The system first combines a plurality of speech rejection features into a feature function in which weights are assigned to each rejection feature in accordance with a recognition accuracy of each rejection feature. Feature values are then calculated for each of the rejection features using the plurality of intermediate recognition results. The system next computes the feature function according to the calculated feature values to determine a rejection decision value. Finally, one of the plurality of intermediate recognition results is accepted as the final recognition result according to the rejection decision value.
    Type: Grant
    Filed: September 22, 1997
    Date of Patent: December 21, 1999
    Assignee: Northern Telecom Limited
    Inventors: Waleed Fakhr, Serge Robillard, Vishwa Gupta, Real Tremblay, Michael Sabourin, Jean-Francois Crespo
  • Patent number: 6006174
    Abstract: The generation of multipulse excitation codes by digitizing an original speech, partitioning the digitized signal into a number of samples, pre-emphasizing the samples, producing linear predictive reflection coefficients from said samples, quantizing these reflection coefficients, converting the quantized reflection coefficients to spectral coefficients and subjecting the spectral coefficients to pitch analysis to obtain a spectral residual signal.
    Type: Grant
    Filed: October 15, 1997
    Date of Patent: December 21, 1999
    Assignee: InterDigital Technology Coporation
    Inventors: Daniel Lin, Brian M. McCarthy
  • Patent number: 5999905
    Abstract: A data processing apparatus for encoding data in which first information data from a first source of information data is supplied together with a reference timing value and subsequently a plurality of successive sources of information data of a predetermined processing unit are input when said first information data is finished being supplied. The data processing apparatus produces an encoding start point for the successive sources of data, as a function of a phase difference value between a predetermined reference timing value obtained before the successive sources of information data are input and a start point of the successive processing unit.
    Type: Grant
    Filed: August 7, 1997
    Date of Patent: December 7, 1999
    Assignee: Sony Corporation
    Inventor: Masaaki Isozaki
  • Patent number: 5999902
    Abstract: A recognizer is provided with a priori probability values (e.g., from some previous recognition) indicating how likely the various words of the recognizer's vocabulary are to occur in the particular context, and recognition "scores" are weighted by these values before a result (or results) is chosen. The recognizer also employs "pruning" whereby low-scoring partial results are discarded, so as to speed the recognition process. To avoid premature pruning of the more likely words, probability values are applied before the pruning decisions are made. A method of applying these probability values is described.
    Type: Grant
    Filed: July 16, 1997
    Date of Patent: December 7, 1999
    Assignee: British Telecommunications public Limited Company
    Inventors: Francis James Scahill, Alison Diane Simons, Steven John Whittaker
  • Patent number: 5995927
    Abstract: A method and an apparatus for performing stochastic matching of a set of input test speech data with a corresponding set of training speech data. In particular, a set of input test speech feature information, having been generated from an input test speech utterance, is transformed so that the stochastic characteristics thereof more closely match the stochastic characteristics of a corresponding set of training speech feature information. The corresponding set of training speech data may, for example, comprise training data which was generated from a speaker having the claimed identity of the speaker of the input test speech utterance. Specifically, in accordance with the present invention, a first covariance matrix representative of stochastic characteristics of input test speech feature information is generated based on the input test speech feature information.
    Type: Grant
    Filed: March 14, 1997
    Date of Patent: November 30, 1999
    Assignee: Lucent Technologies Inc.
    Inventor: Qi P. Li
  • Patent number: 5995934
    Abstract: A recognition method for alpha-numeric strings in a Chinese speech recognition system, uses a special coding scheme to map each of 36 alpha-numeric symbols into an easily remembered Chinese idiom or word consisting of a multiple of Chinese characters. When representing a numeral, each idiom/word starts with the Chinese character for that numeral. When representing an English alphabet letter, each idiom/word will have a first character which starts with that English alphabet letter in its Pinyin form. If it is necessary to include some control words, idiom/words similar in semantics can be used. The method resolves the problem of unreliable recognition when a string of random alpha-numeric symbols or some control words are inputted by voice to a Chinese speech recognition system.
    Type: Grant
    Filed: August 28, 1998
    Date of Patent: November 30, 1999
    Assignee: International Business Machines Corporation
    Inventor: Donald T. Tang
  • Patent number: 5991719
    Abstract: A semantic recognition system of the present invention provides a user interface capable of receiving speech input to a user and an application interface that conveys an input content of the user to an application. The semantic recognition system includes a speech signal input part for receiving input speech signals, a speech recognizer for recognizing a corresponding word based on the input speech signals, a recognized word-semantic number converter including a semantic number-registered word list indicating the correspondence between a semantic number representing a meaning of a word and a registered word belonging to the semantic number, an application interface and an application handling the semantic numbers as data. The corresponding word is recognized by the speech recognizer, based on the speech signals input to the speech signal input part. The recognized word is converted to a corresponding semantic number by the recognized word-semantic number converter.
    Type: Grant
    Filed: September 11, 1998
    Date of Patent: November 23, 1999
    Assignee: Fujistu Limited
    Inventors: Masatomo Yazaki, Toshiaki Gomi, Kenji Yamamoto, Masahide Noda