Patents Examined by Robert Louis Sax
  • Patent number: 6289306
    Abstract: A data processing apparatus includes an input terminal for receiving an audio signal, a 1-bit A/D converter for A/D converting the audio signal so as to obtain a bitstream signal, and a prediction unit for carrying out a prediction step on the bitstream signal so as to obtain a predicted bitstream signal. The data processing apparatus further includes a signal combination unit for combining the bitstream signal and the predicted bitstream signal so as to obtain a residue bitstream signal, and an output terminal for supplying the residual bitstream signal. A recording apparatus or a transmitter apparatus can use the data processing apparatus.
    Type: Grant
    Filed: November 7, 1997
    Date of Patent: September 11, 2001
    Assignee: U.S. Philips Corporation
    Inventors: Renatus J. Van Der Vleuten, Alphons A. M. L. Bruekers, Arnoldus W. J. Oomen
  • Patent number: 6253182
    Abstract: The present invention provides a method for synthesizing speech by modifying the prosody of individual components of a training speech signal and then combining the modified speech segments. The method includes selecting an input speech segment and identifying an output prosody. The prosody of the input speech segment is then changed by independently changing the prosody of a voiced component and an unvoiced component of the input speech signal. These changes produce an output voiced component and an output unvoiced component that are combined to produce an output speech segment. The output speech segment is then combined with other speech segments to form synthesized speech.
    Type: Grant
    Filed: November 24, 1998
    Date of Patent: June 26, 2001
    Assignee: Microsoft Corporation
    Inventor: Alejandro Acero
  • Patent number: 6236969
    Abstract: A wearable communication apparatus is in the form of a self-contained telephone headset that includes an integral antenna, stand-alone power supply and on-board electronics and circuitry for RF and I/R communication. The headset includes a mouthpiece that is rotatably mounted to a central housing that contains the bulk of the apparatus electronics. The mouthpiece includes an ear speaker and microphone, as well as the rechargeable power supply. The rotating end of the mouthpiece includes an array of electrical contacts that are configured to contact a complementary contact array on the central housing. The electrical contacts provide for the communication of electrical power and information between the mouthpiece and its components and the central housing and its components. The headset can be activated by rotation of the mouthpiece into its operative position and deactivated by rotation out of this position.
    Type: Grant
    Filed: July 31, 1998
    Date of Patent: May 22, 2001
    Inventors: Jonathan P. Ruppert, Thomas M. Hintz, Kathleen M. Hintz
  • Patent number: 6236961
    Abstract: The spectral or pitch parameters of a speech signal are quantized, and impulse responses thereof are predicted by using a filter. An orthogonal transform is made of the speech signal, or a signal derived therefrom, or of the impulse responses or signals derived therefrom. The result of the orthogonal transform is entirely or partly quantized to obtain a plurality of pulses. More preferably, these pulses are retrieved recurrently by also using codevectors retrieved from a codebook or collectively quantizing their senses or amplitudes. This method optimizes speech signal coding.
    Type: Grant
    Filed: March 23, 1998
    Date of Patent: May 22, 2001
    Assignee: NEC Corporation
    Inventor: Kazunori Ozawa
  • Patent number: 6233558
    Abstract: A method and apparatus are provided for use in tracing transmission lines from a first location to a second location. The apparatus comprises a multi-channel speech synthesizer, a digital to analog convertor and a demultiplexer. The digital synthesized speech which can take any form is applied to a digital to analog convertor where it is transformed into an analog stream of distinct speech segments. In accordance with the corresponding method, the distinct speech segments are selectively connected by the multiplexer to one or more of the transmission lines to be traced. At the second location, the distinct speech segments are detected. As each distinct speech segment is associated with a particular transmission line, it is possible to distinguish between the many transmission lines which are being simultaneously traced.
    Type: Grant
    Filed: February 11, 1998
    Date of Patent: May 15, 2001
    Assignee: Tempo Research Corporation
    Inventor: Paul L. Whalley
  • Patent number: 6212500
    Abstract: In a method for determining the similarities of sounds across different languages, hidden Markov modelling of multilingual phonemes is employed wherein language-specific as well as language-independent properties are identified by combining of the probability densities for different hidden Markov sound models in various languages.
    Type: Grant
    Filed: March 9, 1999
    Date of Patent: April 3, 2001
    Assignee: Siemens Aktiengesellschaft
    Inventor: Joachim Köhler
  • Patent number: 6212502
    Abstract: The invention is embodied in a computer user interface including an observer capable of observing user behavior, an agent capable of conveying emotion and personality by exhibiting corresponding behavior to a user, and a network linking user behavior observed by said observer and emotion and personality conveyed by said agent. The network can include an observing network facilitating inferencing user emotional and personality states from the behavior observed by the observer as well as an agent network facilitating inferencing of agent behavior from emotion and personality states to be conveyed by the agent. In addition, a policy module can dictate to the agent network desired emotion and personality states to be conveyed by the agent based upon user emotion and personality states inferred by the observing network. Typically, each network is a stochastic model.
    Type: Grant
    Filed: June 30, 1998
    Date of Patent: April 3, 2001
    Assignee: Microsoft Corporation
    Inventors: John Eugene Ball, John S. Breese
  • Patent number: 6185531
    Abstract: A method for improving the associating articles of information or stories with topics associated with specific subjects (subject topics) and with a general topic of words that are not associated with any subject. The inventive method is trained using Hidden Markov Models (HMM) to represent each story with each state in the HMM representing each topic. A standard Expectation and Maximization algorithm, as are known in this art field can be used to maximize the expected likelihood to the method relating the words associated with each topic to that topic. In the method, the probability that each word in a story is related to a subject topic is determined and evaluated, and the subject topics with the lowest probability are discarded. The remaining subject topics are evaluated and a sub-set of subject topics with the highest probabilities over all the words in a story are considered to be the “correct” subject topic set.
    Type: Grant
    Filed: January 9, 1998
    Date of Patent: February 6, 2001
    Assignee: GTE Internetworking Incorporated
    Inventors: Richard M. Schwartz, Toru Imai
  • Patent number: 6185530
    Abstract: A method of determining potential acoustic confusion between at least one new word and at least a portion of existing words of a vocabulary of a speech recognition engine comprises the steps of: a user inputting the at least one new word; computing respective measures between the at least one new word and the at least a portion of existing vocabulary words, the respective measures indicative of acoustic similarity between the at least one word and the at least a portion of existing words; if at least one measure is within a threshold range, indicating results associated with the at least one measure and prompting the user to input an alternative word or additional information pertaining to the at least one new word; and if no measure is within the threshold range, adding the at least one new word to the vocabulary.
    Type: Grant
    Filed: August 14, 1998
    Date of Patent: February 6, 2001
    Assignee: International Business Machines Corporation
    Inventors: Abraham Ittycheriah, Stephane H. Maes
  • Patent number: 6173258
    Abstract: A method for reducing noise distortions in a speech recognition system comprises a feature extractor that includes a noise-suppressor, one or more time cosine transforms, and a normalizer. The noise-suppressor preferably performs a spectral subtraction process early in the feature extraction procedure. The time cosine transforms preferably operate in a centered-mode to each perform a transformation in the time domain. The normalizer calculates and utilizes normalization values to generate normalized features for speech recognition. The calculated normalization values preferably include mean values, left variances and right variances.
    Type: Grant
    Filed: October 22, 1998
    Date of Patent: January 9, 2001
    Assignees: Sony Corporation, Sony Electronics Inc.
    Inventors: Xavier Menendez-Pidal, Miyuki Tanaka, Ruxin Chen, Duanpei Wu
  • Patent number: 6161011
    Abstract: A communications system includes first and second fiber optic links, each including at least one fiber optic cable, and a coaxial distribution plant including coaxial distribution lines and a plurality of amplifiers. A first fiber optic node couples the first fiber optic link to the coaxial distribution plant and a second fiber optic node located proximate to one of the amplifiers of the coaxial distribution plant couples the second fiber optic link to the coaxial distribution plant.
    Type: Grant
    Filed: September 30, 1997
    Date of Patent: December 12, 2000
    Assignee: Scientific-Atlanta, Inc.
    Inventor: Robert C. Loveless
  • Patent number: 6138101
    Abstract: The method of encoding digital data in the present invention enables change of minimum limit of audibility characteristics and/or masking characteristics, which are usually set on the basis of the aural-psychological characteristics of persons with typical hearing, thus changing the allocation of quantized bits to each frequency band and allowing selection of a sound quality which accords with the listener's hearing. The present invention is suitable for ATRAC, a method for compressed encoding for mini-discs.
    Type: Grant
    Filed: December 4, 1997
    Date of Patent: October 24, 2000
    Assignee: Sharp Kabushiki Kaisha
    Inventor: Osamu Fujii
  • Patent number: 6076063
    Abstract: An audio recorder obtains a PCM audio signal from input analog or digital audio data, encodes the PCM audio signal, and stores the encoded signal in a semiconductor memory. The encoding method is selectable from at least two different methods, providing different levels of audio quality. The semiconductor memory may be internal to the audio recorder, or may be an external memory device such as a flash memory card. An audio player decodes the signal stored in the semiconductor memory, and converts the decoded signal to a selected one of at least two output formats.
    Type: Grant
    Filed: October 31, 1997
    Date of Patent: June 13, 2000
    Assignee: Oki Electric Industry Co., Ltd.
    Inventors: Yusaku Unno, Koichi Nakagawa
  • Patent number: 6061652
    Abstract: A HMM device, and a DP matching device, capable of performing word spotting accurately with a small amount of calculation is provided. For that purpose, a code book is provided in which representative vectors of respective clusters are stored in a form searchable by their labels, wherein in HMM, similarity degrees based on Kullbach-Leibler Divergence of distributions of occurrence probabilities of the clusters under respective states and distribution of degrees of input feature vectors to be recognized to the respective clusters are rendered occurrence degrees of the feature vectors from the states and in DP matching, similarity degrees based on Kullbach-Leibler Divergence of distributions of membership degrees of feature vectors forming reference patterns to the respective clusters and distribution of degrees of input feature vectors to the respective clusters are rendered inter-frame similarity degrees of frames of the input patterns and frames of corresponding reference patterns.
    Type: Grant
    Filed: June 18, 1996
    Date of Patent: May 9, 2000
    Assignee: Matsushita Electric Industrial Co., Ltd.
    Inventors: Eiichi Tsuboka, Junichi Nakahashi
  • Patent number: 6047255
    Abstract: A method and system for producing speech signals is disclosed. The speech signals are produced by sequentially reproducing a series of stored speech signal segments. The speech signals may be used to generate a voice message. The signals are formed by reproducing signal segments for system announcement messages and beginning, end and word-pair fragments for "key" words. The system announcement messages and "key" words define a dictionary for the system. The signal segments for word pair fragments correspond to the end portion of one word, a transition to another word and a beginning portion of that other word. The transition between sequentially produced "key" words in a voice message generated from a signal produced from word pair fragments is audibly smooth. The resulting speech signal may correspond to any sequences of words from the dictionary. The method and system are suited for telephony applications, such as voice mail or directory assistance applications.
    Type: Grant
    Filed: December 4, 1997
    Date of Patent: April 4, 2000
    Assignee: Nortel Networks Corporation
    Inventor: Robert Alan Williamson
  • Patent number: 6041301
    Abstract: A method for configuring an audio interface for a speech recognition application in a computer system comprises the steps of: (a) determining from a data storage registry of said speech recognition application whether a microphone operatively associated with said computer system has been previously successfully set up for operation with said speech recognition application; (b) displaying a first graphical user interface having a first user activatable icon for setting up said microphone and a second user activatable icon for adjusting an audio recording level for said microphone; (c) in the event said microphone is not registered as having been previously successfully set up, altering said second icon in appearance and disregarding attempted activation of said second icon; and, (d) in the event said microphone is registered as having been previously successfully set up, respectively initiating said setting up of said microphone and said adjusting of said audio recording level responsive to activation of said
    Type: Grant
    Filed: October 29, 1997
    Date of Patent: March 21, 2000
    Assignee: International Business Machines Corporation
    Inventors: Frank Fado, Peter Guasti, Amado Nassiff, Ronald VanBuskirk
  • Patent number: 6041297
    Abstract: A vocoder according to the present invention includes an analyzer portion and a synthesizer portion. The analyzer portion encodes an input frame of speech on the basis of a candidate excitation selected from a group of candidate excitations stored in memory. Instead of transmitting the actual candidate excitation to the synthesizer portion, the analyzer portion generates and provides to the synthesizer portion a variable length index code that identifies the selected candidate excitation. The synthesizer portion stores in memory the same plurality of candidate excitations as the analyzer portion. The synthesizer portion uses the variable length index code to obtain from its memory the candidate excitation originally selected by the analyzer portion. The synthesizer portion reconstructs the input frame of speech on the basis of the obtained candidate excitation.
    Type: Grant
    Filed: March 10, 1997
    Date of Patent: March 21, 2000
    Assignee: AT&T Corp
    Inventor: Randy G. Goldberg
  • Patent number: 6026361
    Abstract: The present invention, according to one embodiment, comprises a speech intelligibility testing system and method. The invention comprises a sound device for producing a plurality of stimulus words to be heard by a test subject and a display means configured to display a set of word pairs corresponding to a set of contrasting speech sounds. Each word pair comprises two words which are real words with a high degree of familiarity to the test subject, and are displayed whenever a stimulus word is transmitted to the test subject. The first word of the word pair corresponds to the stimulus word, while the second word differs from the first word by at least one of the set of contrasting speech sounds. The invention also comprises a means for the test subject to select one word of the word pair after deciding which of the two words was heard. In accordance with one embodiment, the present invention employs a set of rules to generate vowel and consonant contrasts to be tested.
    Type: Grant
    Filed: December 3, 1998
    Date of Patent: February 15, 2000
    Assignee: Lucent Technologies, Inc.
    Inventor: Susan L. Hura
  • Patent number: 6023677
    Abstract: In a speech recognition method for word sequences that are combined in sentences with defined syntax, syntax information is integrated into a speech model so as to unambiguously identify recurring words through indexing. As a result, the recognition process can be carried out in a manner similar to the situation without integration of the syntax information.
    Type: Grant
    Filed: September 24, 1997
    Date of Patent: February 8, 2000
    Assignee: Daimler Benz AG
    Inventors: Fritz Class, Alfred Kaltenmeier, Ute Kilian, Peter Regel-Brietzmann
  • Patent number: 6023673
    Abstract: A speech coding apparatus and method uses a hierarchy of prototype sets to code an utterance while consuming fewer computing resources. The value of at least one feature of an utterance is measured during each of a series of successive time intervals to produce a series of feature vector signals representing the feature values. A plurality of level subsets of prototype vector signals is computed, wherein each prototype vector signal in a higher level subset is associated with at least one prototype vector signal in a lower level subset. Each level subset contains a plurality of prototype vector signals, with lower level subsets containing more prototypes than higher level subsets. The closeness of the feature value of the first feature vector signal is compared to the parameter values of prototype vector signals in the first level subset of prototype vector signals to obtain a ranked list of prototype match scores for the first feature vector signal and each prototype vector signal in the first level subset.
    Type: Grant
    Filed: June 4, 1997
    Date of Patent: February 8, 2000
    Assignee: International Business Machines Corporation
    Inventors: Raimo Bakis, David Nahamoo, Michael Alan Picheny, Jan Sedivy