Abstract: A voice morphing apparatus having adjustable parameters is described. The disclosed system and method include a voice morphing apparatus that morphs input audio to mask a speaker's identity. Parameter adjustment uses evaluation of an objective function that is based on the input audio and output of the voice morphing apparatus. The voice morphing apparatus includes objectives that are based adversarially on speaker identification and positively on audio fidelity. Thus, the voice morphing apparatus is adjusted to reduce identifiability of speakers while maintaining fidelity of the morphed audio. The voice morphing apparatus may be used as part of an automatic speech recognition system.

Abstract: Systems and methods for training a voice morphing apparatus are described. The voice morphing apparatus is trained to morph input audio data to mask an identity of a speaker. Training is performed by evaluating an objective function that is a function of the input audio data and an output of the voice morphing apparatus. The objective function may have a first term that is based on speaker identification and a second term that is based on audio fidelity. By optimizing the objective function, parameters of the voice morphing apparatus may be adjusted so as to reduce a confidence of speaker identification and maintain an audio fidelity of the morphed audio data. The voice morphing apparatus, once trained, may be used as part of an automatic speech recognition system.

Abstract: A voice morphing apparatus having adjustable parameters is described. The disclosed system and method include a voice morphing apparatus that morphs input audio to mask a speaker's identity. Parameter adjustment uses evaluation of an objective function that is based on the input audio and output of the voice morphing apparatus. The voice morphing apparatus includes objectives that are based adversarially on speaker identification and positively on audio fidelity. Thus, the voice morphing apparatus is adjusted to reduce identifiability of speakers while maintaining fidelity of the morphed audio. The voice morphing apparatus may be used as part of an automatic speech recognition system.

Abstract: Systems and methods for training a voice morphing apparatus are described. The voice morphing apparatus is trained to morph input audio data to mask an identity of a speaker. Training is performed by evaluating an objective function that is a function of the input audio data and an output of the voice morphing apparatus. The objective function may have a first term that is based on speaker identification and a second term that is based on audio fidelity. By optimizing the objective function, parameters of the voice morphing apparatus may be adjusted so as to reduce a confidence of speaker identification and maintain an audio fidelity of the morphed audio data. The voice morphing apparatus, once trained, may be used as part of an automatic speech recognition system.

Abstract: Method and apparatus for reducing a size of databases required for recorded speech data.

Abstract: Method and apparatus for diphone or concatenative synthesis to compensate for insufficient or missing diphones.

Abstract: Method and apparatus for reducing a size of databases required for recorded speech data.

Abstract: A taxonomy engine in a software architecture generates a taxonomy dataset establishing the group of well formed commands, and at least one command generator of the system is adapted to generate a well formed command using the taxonomy dataset. The taxonomy engine is configured to deliver the taxonomy dataset to the command generator, and the command generator is configured to deliver the well formed command to the controller.

Abstract: A graphic user interface system for use with a content based retrieval system includes an active display having display areas. For example, the display areas include a main area providing an overview of database contents by displaying representative samples of the database contents. The display areas also include one or more query areas into which one or more of the representative samples can be moved from the main area by a user employing gesture based interaction. A query formulation module employs the one or more representative samples moved into the query area to provide feedback to the content based retrieval system.

Abstract: A spray nozzle assembly comprising a nozzle body and a separate nozzle body insert adapted for removable snap action engagement with the body. The nozzle body insert defines a liquid flow passage that includes an inlet section for communicating with a liquid inlet, a metering orifice for accelerating the liquid flow stream, and a downstream expansion section. The body insert further includes a venturi passage communicating with the expansion section for drawing ambient air into the liquid flow stream for stabilizing the liquid prior to discharge from the nozzle. In the illustrated embodiment, the expansion chamber communicates with a transverse passage of the nozzle body, which in turn communicates with a laterally oriented discharge orifice.

Abstract: An apparatus, system, and method are disclosed for managing multiple copy versions of a source volume. In one embodiment, the apparatus includes a replication record management module, a pre-pairing record management module, and a copy record module. The replication record management module is configured to maintain a current replication record that is descriptive of a current copy version of the source volume. The pre-pairing record management module is configured to maintain a future pre-pairing record that is descriptive of a future copy version of the source volume. The copy record module is configured to create a copy record from a pre-copy record. The pre-copy record may be either the current replication record or the future pre-pairing record. The apparatus, system, and method beneficially maintain multiple records to describe different states for a particular copy version and dynamically handle changes to a source pool, a target pool, or both in a data copy environment.

Abstract: A taxonomy engine in a software architecture generates a taxonomy dataset establishing the group of well formed commands, and at least one command generator of the system is adapted to generate a well formed command using the taxonomy dataset. The taxonomy engine is configured to deliver the taxonomy dataset to the command generator, and the command generator is configured to deliver the well formed command to the controller.

Abstract: A spray nozzle assembly comprising a nozzle body and a separate nozzle body insert adapted for removable snap action engagement with the body. The nozzle body insert defines a liquid flow passage that includes an inlet section for communicating with a liquid inlet, a metering orifice for accelerating the liquid flow stream, and a downstream expansion section. The body insert further includes a venturi passage communicating with the expansion section for drawing ambient air into the liquid flow stream for stabilizing the liquid prior to discharge from the nozzle. In the illustrated embodiment, the expansion chamber communicates with a transverse passage of the nozzle body, which in turn communicates with a laterally oriented discharge orifice.

Abstract: Disclosed is a system, method, and program for data backup. A backup copy of source data is created. A backup dataset inventory is created when the backup copy is created. The backup dataset inventory includes a backup dataset identifier and an originating source volume identifier for cach dataset of the source data. The backup copy is copied to a storage medium. A storage media inventory is created when copying the backup copy to the storage medium. The storage media inventory includes the originating source volume identifier and a storage media identifier for each dataset of the source data. This single backup scheme eliminates having to issue both image copies for individual dataset recovery, as well as, separate full volume dumps for recover of failed physical volumes or to recover an entire application.

Abstract: A method of copying a body of source data is shown, with rapid creation of an a backup dataset inventory. While write operations to the source data are temporarily suspended, a backup manager conducts an instant virtual copy of the source data creating a backup copy. Also while write operations are being suspended, the backup manager captures contents of a source dataset inventory cross-referencing datasets in the source data and locations in the body of source data where the datasets are stored. After the copy operation completes and writes to the source data resume, the backup manager adds the captured backup contents to a backup dataset inventory cross-referencing datasets in the backup copy and locations where the backup copy datasets are stored in the backup copy.

Abstract: A storage management system, apparatus, and method to increase the storage capacity of data storage media. Applicants' method uses a data storage device comprising a fixed device architecture, where that data storage device is capable of operating in a first capacity mode or in a second capacity mode, and where that data storage device is capable of switching between the first capacity mode and the second capacity mode. In certain embodiments, the first capacity mode utilizes a 22 bit blockid format and the second capacity mode utilizes a 32 bit blockid format. In other embodiments, the first capacity mode utilizes a 32 bit blockid format and the second capacity mode utilizes a 22 bit blockid format. A computer code product comprising a data management system which includes an operating system and data storage device microcode, which supports the capability to switch between alternative information storage architectures, and thereby, increase the capacity utilization of data storage media.

Abstract: A method of copying a body of source data is shown, with rapid creation of an a backup dataset inventory. While write operations to the source data are temporarily suspended, a backup manager conducts an instant virtual copy of the source data creating a backup copy. Also while write operations are being suspended, the backup manager captures contents of a source dataset inventory cross-referencing datasets in the source data and locations in the body of source data where the datasets are stored. After the copy operation completes and writes to the source data resume, the backup manager adds the captured backup contents to a backup dataset inventory cross-referencing datasets in the backup copy and locations where the backup copy datasets are stored in the backup copy.

Abstract: A storage management system, apparatus, and method to increase the storage capacity of data storage media. Applicants' method uses a data storage device comprising a fixed device architecture, where that data storage device is capable of operating in a first capacity mode or in a second capacity mode, and where that data storage device is capable of switching between the first capacity mode and the second capacity mode. In certain embodiments, the first capacity mode utilizes a 22 bit blockid format and the second capacity mode utilizes a 32 bit blockid format. In other embodiments, the first capacity mode utilizes a 32 bit blockid format and the second capacity mode utilizes a 22 bit blockid format.

Abstract: A speech synthesizer customization system provides a mechanism for generating a hierarchical customized user database. The customization system has a template management tool for generating the templates based on customization data from a user and associated replicated dynamic synthesis data from a text-to-speech (TTS) synthesizer. The replicated dynamic synthesis data is arranged in a dynamic data structure having hierarchical levels. The customization system further includes a user database that supplements a standard database of the synthesizer. The tool populates the user database with the templates such that the templates enable the user database to uniformly override subsequently generated speech synthesis data at all hierarchical levels of the dynamic data structure.

Abstract: The concatenative speech synthesizer employs demi-syllable subword units to generate speech. The synthesizer is based on a source-filter model that uses source signals that correspond closely to the human glottal source and that uses filter parameters that correspond closely to the human vocal tract. Concatenation of the demi-syllable units is facilitated by two separate cross face techniques, one applied in the time domain in the demi-syllable source signal waveforms, and one applied in the frequency domain by interpolating the corresponding filter parameters of the concatenated demi-syllables. The dual cross fade technique results in natural sounding synthesis that avoids time-domain glitches without degrading or smearing characteristic resonances in the filter domain.