Abstract: Disclosed are video conferencing systems, devices, architectures, and methods for transcoding, transrating, and the like, to facilitate video streaming in a distributed arrangement. An exemplary translator in accordance with embodiments can include: an input configured to receive a first video stream in a first format, the first video stream being from a first media switch, the first media switch being associated with a first stream group having one or more first endpoints; and an output configured to provide a second video stream in a second format, the second video stream being sent to a second media switch, the second media switch being associated with a second stream group having one or more second endpoints, whereby the translator is configured to convert from the first to the second format.

Abstract: Disclosed are video conferencing systems, devices, architectures, and methods for using media notifications to coordinate switching between video in a distributed arrangement. An exemplary media switch in accordance with embodiments can include: a first interface configured for a first type communication with an endpoint; a second interface configured for the first type communication with another media switch, the second interface being configured to receive a first video stream having a first characteristic and a second video stream having a second characteristic; a third interface configured for a second type communication with a stream controller, the stream controller being configured to provide a notification; and a fourth interface configured for the second type communication with a controlling server, whereby the media switch is configured to re-target an active stream in response to the notification or a difference between the first and second characteristics.

Abstract: According to an embodiment of the present invention, an apparatus for performing video conferencing is provided that includes an I-frame injector element operable to intercept I-frame requests from one or more end points and to attempt to service the I-frame requests such that at least a portion of the requests are prevented from propagating back to an originating sender. In more specific embodiments, when a receiver endpoint sends a fast video update (FVU) request upstream, it is intercepted by the I-frame injector element and rather than passing the FVU request to the sender the I-frame injector element replaces a next P-frame from the sender with an I-frame, whereby the I-frame is constructed so that when decoded, it matches the P-frame that it replaced. In still more detailed embodiments, the I-frame injector element operates in one of three modes that are associated with bandwidth parameters.

Abstract: An audio mixer on a first device receives one or more incoming audio streams. Each of the one or more incoming audio streams has an associated timestamp. The audio mixer generates a mixed audio stream from the one or more incoming audio streams. The audio mixer determines differences in the time base of each of the one or more incoming audio streams and the time base for the mixed audio stream. The audio mixer generates mapping parameters associated with the determined differences and transforms the timestamp of each of the one or more incoming audio streams to a corresponding output timestamp associated with the mixed audio stream according to the mapping parameters. the mapping parameters are provided to a video mixer for similar processing and transformation such that the mixed audio stream is in synchronization with a mixed video stream.

Abstract: A method for executing a video conference is provided that includes receiving one or more audio streams associated with a video conference from one or more end points and determining an active speaker associated with one of the end points. Audio information associated with the active speaker may be received at one or more media switches. One or more video streams may be suppressed except for a selected video stream associated with the active speaker, the selected video stream propagating to one or more of the media switches during the video conference. The selected video stream may be replicated such that it may be communicated to one or more of the end points associated with a selected one of the media switches.

Abstract: A method for executing a video conference is provided that includes receiving one or more audio streams associated with a video conference from one or more end points and determining an active speaker associated with one of the end points. Audio information associated with the active speaker may be received at one or more media switches. One or more video streams may be suppressed except for a selected video stream associated with the active speaker, the selected video stream propagating to one or more of the media switches during the video conference. The selected video stream may be replicated such that it may be communicated to one or more of the end points associated with a selected one of the media switches.

Abstract: A method for executing a video conference is provided that includes receiving one or more audio streams associated with a video conference from one or more end points and determining an active speaker associated with one of the end points. Audio information associated with the active speaker may be received at one or more media switches. One or more video streams may be suppressed except for a selected video stream associated with the active speaker, the selected video stream propagating to one or more of the media switches during the video conference. The selected video stream may be replicated such that it may be communicated to one or more of the end points associated with a selected one of the media switches.

Abstract: A method for executing a video conference is provided that includes receiving one or more audio streams associated with a video conference from one or more end points and determining an active speaker associated with one of the end points. Audio information associated with the active speaker may be received at one or more media switches. One or more video streams may be suppressed except for a selected video stream associated with the active speaker, the selected video stream propagating to one or more of the media switches during the video conference. The selected video stream may be replicated such that it may be communicated to one or more of the end points associated with a selected one of the media switches.

Abstract: A method for implementing a noise suppressor in a speech recognition system comprises a filter bank for separating source speech data into discrete frequency sub-bands to generate filtered channel energy, and a noise suppressor for weighting the frequency sub-bands to improve the signal-to-noise ratio of the resultant noise-suppressed channel energy. The noise suppressor preferably includes a noise calculator for calculating background noise values, a speech energy calculator for calculating speech energy values for each channel of the filter bank, and a weighting module for applying calculated weighting values to the projected channel energy to generate the noise-suppressed channel energy.

Abstract: A system and method for speech verification using out-of-vocabulary models includes a speech recognizer that has a model bank with system vocabulary word models, a garbage model, and one or more noise models. The model bank may reject an utterance or other sound as an invalid vocabulary word when the model bank identifies the utterance or other sound as corresponding to the garbage model or the noise models. Initial noise models may be selectively combined into a pre-determined number of final noise model clusters to effectively reduce the number of noise models that are utilized by the model bank of the speech recognizer to verify system vocabulary words.

Abstract: A method for performing microphone conversions in a speech recognition system comprises a speech module that simultaneously captures an identical input signal using both an original microphone and a final microphone. The original microphone is also used to record an original training database. The final microphone is also used to capture input signals during normal use of the speech recognition system. A characterization module then analyzes the recorded identical input signal to generate characterization values that are subsequently utilized by a conversion module to convert the original training database into a final training database. A training program then uses the final training database to train a recognizer in the speech module in order to optimally perform a speech recognition process, in accordance with the present invention.

Abstract: A method for utilizing validity constraints in a speech endpoint detector comprises a validity manager that may utilize a pulse width module to validate utterances that include a plurality of energy pulses during a certain time period. The validity manager also may utilize a minimum power module to ensure that speech energy below a pre-determined level is not classified as a valid utterance. In addition the validity manager may use a duration module to ensure that valid utterances fall within a specified duration. Finally, the validity manager may utilize a short-utterance minimum power module to specifically distinguish an utterance of short duration from background noise based on the energy level of the short utterance.

Abstract: The present invention comprises a system and method for speech verification using a confidence measure that includes a speech verifier which compares a differential score for a recognized word to a predetermined threshold value, where a recognized word is the word model that produced the highest recognition score. In one embodiment, a single threshold is used for each word in a vocabulary. In another embodiment, each word model has an associated threshold, so that a differential score for a recognized word is compared to a unique threshold associated with that word. In a further embodiment, pairs of confused words in the vocabulary are dealt with separately. If a confused word is the recognized word, the speech verifier compares the differential score to a threshold that depends on the word model that produced the next-highest recognition score. Different values for the various thresholds may maximize rejection accuracy or recognition accuracy.

Abstract: A method for implementing a speech verification system for use in a noisy environment comprises the steps of generating a confidence index for an utterance using a speech verifier, and controlling the speech verifier with a processor, wherein the utterance contains frames of sound energy. The speech verifier includes a noise suppressor, a pitch detector, and a confidence determiner. The noise suppressor suppresses noise in each frame in the utterance by summing a frequency spectrum for each frame with frequency spectra of a selected number of previous frames to produce a spectral sum. The pitch detector applies a spectral comb window to each spectral sum to produce correlation values for each frame in the utterance. The pitch detector also applies an alternate spectral comb window to each spectral sum to produce alternate correlation values for each frame in the utterance. The confidence determiner evaluates the correlation values to produce a frame confidence measure for each frame in the utterance.

Abstract: A method for effectively suppressing background noise in a speech detection system comprises a filter bank for separating source speech data into discrete frequency sub-bands to generate filtered channel energy, and a noise suppressor for weighting the frequency sub-bands to improve the signal-to-noise ratio of the resultant noise-suppressed channel energy. The noise suppressor preferably includes a subspace module for using a Karhunen-Loeve transformation to create a subspace based on the background noise, a projection module for generating projected channel energy by projecting the filtered channel energy onto the created subspace, and a weighting module for applying calculated weighting values to the projected channel energy to generate the noise-suppressed channel energy.

Abstract: A method for implementing a speech recognition system for use during conditions with background noise includes the steps of calculating, in real-time, sequential short-term delta energy parameters for speech energy from a spoken utterance, determining threshold values in the speech energy, and identifying a beginning point and an ending point for the spoken utterance based on the relationship between the threshold values and the short-term delta energy parameters.

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.

Abstract: A method and an apparatus for a parameter sharing speech recognition system are provided. Speech signals are received into a processor of a speech recognition system. The speech signals are processed using a speech recognition system hosting a shared hidden Markov model (HMM) produced by generating a number of phoneme models, some of which are shared. The phoneme models are generated by retaining as a separate phoneme model any triphone model having a number of trained frames available that exceeds a prespecified threshold. A shared phoneme model is generated to represent each of the groups of triphone phoneme models for which the number of trained frames having a common biphone exceed the prespecified threshold. A shared phoneme model is generated to represent each of the groups of triphone phoneme models for which the number of trained frames having an equivalent effect on a phonemic context exceed the prespecified threshold.

Abstract: Apparatus and method for speech recognition control of apparel manufacture equipment, such as a sewing machine, is provided. The invention includes a device for recognizing and translating an operator's verbal command into a digital control signal; a communication device such as a microphone for inputting the operator's verbal command into the recognizing and translating device; and interfacing means for presenting the digital control signal to the apparel manufacture equipment in a form recognized and accepted by the equipment. The method for voice control of apparel manufacture equipment according to the present invention comprises the steps of receiving an operator's verbal command; recognizing and translating the verbal command into a digital control signal; and routing this digital control signal to the apparel manufacture equipment in a form recognized by an actable upon by the equipment. An infrared light linkage may be employed to transmit commands from an operator to the machine's control circuitry.