Lucent Technologies Inc.

Sorenson IP Holdings, LLC

Paul Wesley Cohrs

Donald Marion Keen

Ellen Anne Keen

Mitra P Deldar

John Arthur Karpicke

Barry L Lively

A computer-implemented method to generate an audio output signal is disclosed. The method may include receiving an audio input signal at an automatic gain control (AGC) unit. The method may further include receiving a volume setting indicator signal at the AGC unit. Further, the method may include setting one or more operational parameters for the AGC unit based on the volume setting indicator signal. In addition, the method may include applying a gain to the audio input signal based on the one or more operational parameters to generate an audio output signal at a desired output level.

Volume-dependent automatic gain control

A method and apparatus for speech recognition in which a single criterion or set of criteria is selected manually by the user, from plural classes of recognition criteria. The stored classes of recognition criteria include a default class optimized for an average user in normal conditions, at least one class having a probability of recognition greater than said default class, and at least one class having a probability of recognition less than said default class. Accordingly, the user may select that class of criteria which provides the best results for him or her, as measured by greater accuracy (fewer false positive detections) or fewer instances of non-rejection. An utterance is compared to one or more models of speech to determine a similarity metric for each such comparison. The model of speech which most closely matches the utterance is determined based on the one or more similarity metrics. The similarity metric corresponding to the most closely matching model of speech is analyzed to determine whether the similarity metric satisfies the criteria of the user-selected class. The present application has application to many problems in speech recognition including isolated word recognition and command spotting. Illustrative embodiments of the invention in the context of telecommunications instruments are provided.

User selectable multiple threshold criteria for voice recognition

A method for automatically confirming verbal commands issued by a user and received by an automatic speech recognition system. Each verbal command is associated with a command operator set in which one or more command operators are stored. After the user vocalizes a recognized verbal command, the automatic speech recognition system awaits vocalization of a valid command operator from an associated stored command operator set for a pre-determined period of time. During this waiting period a non-intrusive indicator such as a light or a low volume tone notifies the user that the automatic speech recognition system is awaiting or ready to receive an appropriate command operator. If the user vocalizes a valid and recognized command operator during the waiting period, then the automatic speech recognition system executes the verbal command using the command operator and issues a confirmation to the user that the verbal command has been executed. Otherwise, the automatic speech recognition system returns to its idle state awaiting a further verbal command.

Method of implicit confirmation for automatic speech recognition

A recognition criterion or set of recognition criteria are updated automatically, over time, in accordance with the speech input of the user(s). Each input utterance is compared to one or more models of speech to determine a similarity metric for each such comparison. A model of speech which most closely matches the utterance is determined based on the one or more similarity metrics. The similarity metric corresponding to the most closely matching model of speech is analyzed to determine whether the similarity metric satisfies the selected set of recognition criteria. The recognition criteria are automatically altered during use or 'on-the-fly', so that more appropriate criteria (and associated thresholds) may be used to either increase the probability of recognition or decrease the incidence of false positive results. Illustratively, if a voice sample results in a near miss of a template, a more liberal criterion is thereafter employed to increase the probability of recognition for subsequent input. Parametric histories of recognition and near misses followed by recognition are kept with periodic alteration of the criteria values to correspond to these histories. Additionally, parametric histories of false alarms are maintained and used to update criteria values in combination with recognition histories.

Telecommunications instrument employing variable criteria speech

A telephone ringing system in which one or more user-selected sound segments are received using the microphone portion of a telecommunications instrument, stored in digital or analog form, and audibly reproduced using the loudspeaker portion of the telecommunications instrument when a ring signal is detected to provide a distinctive, personalized indication of an incoming call.

Growing community of inventors

Indianapolis, IN, United States of America

Paul Wesley Cohrs