Abstract: Apparatuses, systems, methods, and media for filtering a data stream are provided. The data stream is partitioned into a plurality of data stream segments. An acoustic parameter is measured in each of the data stream segments. It is determined whether the acoustic parameter satisfies a first predetermined condition. The first predetermined condition includes a number of variances, in which the acoustic parameter exceeds a predetermined variance threshold, exceeding a predetermined number threshold. An extraneous portion of the data stream is identified in which the first predetermined condition is satisfied. It is determined whether the extraneous portion satisfies a second predetermined condition in the data stream. The extraneous portion is deleted from the data stream to produce a filtered data stream in response to the second predetermined condition being satisfied.

Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for captioning a media presentation. The method includes receiving automatic speech recognition (ASR) output from a media presentation and a transcription of the media presentation. The method includes selecting via a processor a pair of anchor words in the media presentation based on the ASR output and transcription and generating captions by aligning the transcription with the ASR output between the selected pair of anchor words. The transcription can be human-generated. Selecting pairs of anchor words can be based on a similarity threshold between the ASR output and the transcription. In one variation, commonly used words on a stop list are ineligible as anchor words. The method includes outputting the media presentation with the generated captions. The presentation can be a recording of a live event.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for detecting and correcting abnormal stress patterns in unit-selection speech synthesis. A system practicing the method detects incorrect stress patterns in selected acoustic units representing speech to be synthesized, and corrects the incorrect stress patterns in the selected acoustic units to yield corrected stress patterns. The system can further synthesize speech based on the corrected stress patterns. In one aspect, the system also classifies the incorrect stress patterns using a machine learning algorithm such as a classification and regression tree, adaptive boosting, support vector machine, and maximum entropy. In this way a text-to-speech unit selection speech synthesizer can produce more natural sounding speech with suitable stress patterns regardless of the stress of units in a unit selection database.

Abstract: A method of detecting pre-determined phrases to determine compliance quality of an agent includes determining a presence of a predetermined input based on a comparison between stored pre-determined phrases and a received communication, and determining a compliance rating of the agent based on a presence of a pre-determined phrase associated with the predetermined input in the communication.

Abstract: Apparatuses, systems, methods, and media for filtering a data stream are provided. The data stream is partitioned into a plurality of data stream segments. An acoustic parameter is measured in each of the data stream segments. It is determined whether the acoustic parameter satisfies a first predetermined condition. The first predetermined condition includes a number of variances, in which the acoustic parameter exceeds a predetermined variance threshold, exceeding a predetermined number threshold. An extraneous portion of the data stream is identified in which the first predetermined condition is satisfied. It is determined whether the extraneous portion satisfies a second predetermined condition in the data stream. The extraneous portion is deleted from the data stream to produce a filtered data stream in response to the second predetermined condition being satisfied.

Abstract: Apparatuses, systems, methods, and media for filtering a data stream are provided. The data stream is analyzed based on an acoustic parameter to determine extraneous portions in which a first predetermined condition is satisfied. When a first extraneous portion is separated from a second extraneous portion by a non-extraneous portion in which the first predetermined condition is not satisfied, it is determined whether the first extraneous portion being separated from the second extraneous portion by the non-extraneous portion satisfies a second predetermined condition. At least one of the first extraneous portion and the second extraneous portion is deleted from the data stream to produce a filtered data stream in response to determining the second predetermined condition is satisfied.

Abstract: A method of detecting pre-determined phrases to determine compliance quality of an agent includes determining a presence of a predetermined input based on a comparison between stored pre-determined phrases and a received communication, and determining a compliance rating of the agent based on a presence of a pre-determined phrase associated with the predetermined input in the communication.

Abstract: A method of detecting pre-determined phrases to determine compliance quality includes determining whether a precursor event has occurred based on a comparison between stored pre-determined phrases and a received communication, and determining a compliance rating based on a presence of a pre-determined phrase associated with the precursor event in the communication.

Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for captioning a media presentation. The method includes receiving automatic speech recognition (ASR) output from a media presentation and a transcription of the media presentation. The method includes selecting via a processor a pair of anchor words in the media presentation based on the ASR output and transcription and generating captions by aligning the transcription with the ASR output between the selected pair of anchor words. The transcription can be human-generated. Selecting pairs of anchor words can be based on a similarity threshold between the ASR output and the transcription. In one variation, commonly used words on a stop list are ineligible as anchor words. The method includes outputting the media presentation with the generated captions. The presentation can be a recording of a live event.

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for unit selection synthesis. The method causes a computing device to add a supplemental phoneset to a speech synthesizer front end having an existing phoneset, modify a unit preselection process based on the supplemental phoneset, preselect units from the supplemental phoneset and the existing phoneset based on the modified unit preselection process, and generate speech based on the preselected units. The supplemental phoneset can be a variation of the existing phoneset, can include a word boundary feature, can include a cluster feature where initial consonant clusters and some word boundaries are marked with diacritics, can include a function word feature which marks units as originating from a function word or a content word, and/or can include a pre-vocalic or post-vocalic feature. The speech synthesizer front end can incorporates the supplemental phoneset as an extra feature.

Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for captioning a media presentation. The method includes receiving automatic speech recognition (ASR) output from a media presentation and a transcription of the media presentation. The method includes selecting via a processor a pair of anchor words in the media presentation based on the ASR output and transcription and generating captions by aligning the transcription with the ASR output between the selected pair of anchor words. The transcription can be human-generated. Selecting pairs of anchor words can be based on a similarity threshold between the ASR output and the transcription. In one variation, commonly used words on a stop list are ineligible as anchor words. The method includes outputting the media presentation with the generated captions. The presentation can be a recording of a live event.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating speech. One variation of the method is from a server side, and another variation of the method is from a client side. The server side method, as implemented by a network-based automatic speech processing system, includes first receiving, from a network client independent of knowledge of internal operations of the system, a request to generate a text-to-speech voice. The request can include speech samples, transcriptions of the speech samples, and metadata describing the speech samples. The system extracts sound units from the speech samples based on the transcriptions and generates an interactive demonstration of the text-to-speech voice based on the sound units, the transcriptions, and the metadata, wherein the interactive demonstration hides a back end processing implementation from the network client. The system provides access to the interactive demonstration to the network client.

Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for captioning a media presentation. The method includes receiving automatic speech recognition (ASR) output from a media presentation and a transcription of the media presentation. The method includes selecting via a processor a pair of anchor words in the media presentation based on the ASR output and transcription and generating captions by aligning the transcription with the ASR output between the selected pair of anchor words. The transcription can be human-generated. Selecting pairs of anchor words can be based on a similarity threshold between the ASR output and the transcription. In one variation, commonly used words on a stop list are ineligible as anchor words. The method includes outputting the media presentation with the generated captions. The presentation can be a recording of a live event.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for detecting and correcting abnormal stress patterns in unit-selection speech synthesis. A system practicing the method detects incorrect stress patterns in selected acoustic units representing speech to be synthesized, and corrects the incorrect stress patterns in the selected acoustic units to yield corrected stress patterns. The system can further synthesize speech based on the corrected stress patterns. In one aspect, the system also classifies the incorrect stress patterns using a machine learning algorithm such as a classification and regression tree, adaptive boosting, support vector machine, and maximum entropy. In this way a text-to-speech unit selection speech synthesizer can produce more natural sounding speech with suitable stress patterns regardless of the stress of units in a unit selection database.

Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for captioning a media presentation. The method includes receiving automatic speech recognition (ASR) output from a media presentation and a transcription of the media presentation. The method includes selecting via a processor a pair of anchor words in the media presentation based on the ASR output and transcription and generating captions by aligning the transcription with the ASR output between the selected pair of anchor words. The transcription can be human-generated. Selecting pairs of anchor words can be based on a similarity threshold between the ASR output and the transcription. In one variation, commonly used words on a stop list are ineligible as anchor words. The method includes outputting the media presentation with the generated captions. The presentation can be a recording of a live event.

Abstract: Apparatuses, systems, methods, and media for filtering a data stream are provided. The data stream is analyzed based on an acoustic parameter to determine extraneous portions in which a first predetermined condition is satisfied. When a first extraneous portion is separated from a second extraneous portion by a non-extraneous portion in which the first predetermined condition is not satisfied, it is determined whether the first extraneous portion being separated from the second extraneous portion by the non-extraneous portion satisfies a second predetermined condition. At least one of the first extraneous portion and the second extraneous portion is deleted from the data stream to produce a filtered data stream in response to determining the second predetermined condition is satisfied.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for detecting and correcting abnormal stress patterns in unit-selection speech synthesis. A system practicing the method detects incorrect stress patterns in selected acoustic units representing speech to be synthesized, and corrects the incorrect stress patterns in the selected acoustic units to yield corrected stress patterns. The system can further synthesize speech based on the corrected stress patterns. In one aspect, the system also classifies the incorrect stress patterns using a machine learning algorithm such as a classification and regression tree, adaptive boosting, support vector machine, and maximum entropy. In this way a text-to-speech unit selection speech synthesizer can produce more natural sounding speech with suitable stress patterns regardless of the stress of units in a unit selection database.

Abstract: Methods, apparatuses, and media for filtering a data stream are provided. The data stream is partitioned into a plurality of data stream segments. An acoustic parameter of each of the data stream segments is measured, and it is determined whether the acoustic parameter of each of the data stream segments satisfies a predetermined condition. Extraneous segments of the data stream segments are identified in which the predetermined condition is satisfied, and it is determined whether the extraneous segments have a predetermined relationship in the data stream. The extraneous segments are deleted from the data stream to produce a filtered data stream in response to the extraneous segments having the predetermined relationship.

Abstract: A method of detecting pre-determined phrases to determine compliance quality includes determining whether a precursor event has occurred based on a comparison between stored pre-determined phrases and a received communication, and determining a compliance rating based on a presence of a pre-determined phrase associated with the precursor event in the communication.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating speech. One variation of the method is from a server side, and another variation of the method is from a client side. The server side method, as implemented by a network-based automatic speech processing system, includes first receiving, from a network client independent of knowledge of internal operations of the system, a request to generate a text-to-speech voice. The request can include speech samples, transcriptions of the speech samples, and metadata describing the speech samples. The system extracts sound units from the speech samples based on the transcriptions and generates an interactive demonstration of the text-to-speech voice based on the sound units, the transcriptions, and the metadata, wherein the interactive demonstration hides a back end processing implementation from the network client. The system provides access to the interactive demonstration to the network client.