1073 results about "Silence" patented technology

An alarm suspend system utilizes an alarm trigger responsive to physiological parameters and corresponding limits on those parameters. The parameters are associated with both fast and slow treatment times corresponding to length of time it takes for a person to respond to medical treatment for out-of-limit parameter measurements. Audible and visual alarms respond to the alarm trigger. An alarm silence button is pressed to silence the audible alarm for a predetermined suspend time. The audible alarm is activated after the suspend time has lapsed. Longer suspend times are associated with slow treatment parameters and shorter suspend times are associated with fast treatment parameters.

Audio frames are classified as either speech, non-transient background noise, or transient noise events. Probabilities of speech or transient noise event, or other metrics may be calculated to indicate confidence in classification. Frames classified as speech or noise events are not used in updating models (e.g., spectral subtraction noise estimates, silence model, background energy estimates, signal-to-noise ratio) of non-transient background noise. Frame classification affects acceptance / rejection of recognition hypothesis. Classifications and other audio related information may be determined by circuitry in a headset, and sent (e.g., wirelessly) to a separate processor-based recognition device.

A method and apparatus for audio compensation is disclosed. If audio input components and audio output components are not driven by a common clock (e.g., input and output systems are separated by a network, different clock signals in a single computer system), input and output sampling rates may differ. Also, network routing of the digital audio data may not be consistent. Both clock synchronization and routing considerations can affect the digital audio output. To compensate for the timing irregularities caused by clock synchronization differences and / or routing changes, the present invention adjusts periods of silence in the digital audio data being output. The present invention thereby provides an improved digital audio output.

For machine segmenting of speech, first utterances from a database of known spoken words are classified and segmented into three broad phonetic classes (BPC) voiced, unvoiced, and silence. Next, using preliminary segmentation positions as anchor points, sequence-constrained vector quantization is used for further segmentation into phoneme-like units. Finally, exact tuning to the segmented phonemes is done through Hidden-Markov Modelling and after training a diphone set is composed for further usage.

A speech-to-text conversion module uses a central database of user speech profiles to convert speech to text. Incoming audio information is fragmented into numerous audio fragments based upon detecting silence. The audio information is also converted to numerous text files by any number of speech engines. Each text file is then fragmented into numerous text fragments based upon the boundaries established during the audio fragmentation. Each set of text fragments from the different speech engines corresponding to a single audio fragments is then compared. The best approximation of the audio fragment is produced from the set of text fragments; a hybrid may be produced. If no agreement is reached, the audio fragment and set the text fragments are sent to human agents who verify and edit to produce a final edited text fragment that best corresponds to the audio fragment. Fragmentation that produces overlapping audio fragments requires splicing of the final text fragments to produce the output text file.

A beeper system that includes a beeper attached to a flexible band. The flexible band is attached to the child, such as around the wrist, waist or neck, to prevent the child from removing the beeper. The beeper is programmed to reach a no shut off mode wherein a speaker outputs an audible output of increasing loudness until the beeper is turned off by keyswitch controlled or kept by the supervising adult. The keyswitch is also used to disconnect the flexible band to allow removal of the beeper. A wearer silence button is provided to allow for a warning period before the no shut off mode is reached.

Audio frames are classified as either speech, non-transient background noise, or transient noise events. Probabilities of speech or transient noise event, or other metrics may be calculated to indicate confidence in classification. Frames classified as speech or noise events are not used in updating models (e.g., spectral subtraction noise estimates, silence model, background energy estimates, signal-to-noise ratio) of non-transient background noise. Frame classification affects acceptance / rejection of recognition hypothesis. Classifications and other audio related information may be determined by circuitry in a headset, and sent (e.g., wirelessly) to a separate processor-based recognition device.

In a speech recognition system which recognizes a spoken utterance consisting of a sequence of spoken words and, in response, outputs a sequence of decoded words, a method for automatically punctuating the sequence of decoded words is provided. In a vocabulary of items including words, silences, and punctuation marks, assigning at least one baseform to each punctuation mark corresponding to one of silence and a non-word noise. Additionally, the method includes the step of automatically inserting a subject punctuation mark at a given point in the sequence of decoded words when an acoustic score and a language model score associated with the subject punctuation mark produce a higher combined likelihood than the acoustic score and the language model score associated with any other item in the vocabulary for the given point in the sequence of decoded words.

The present invention relates to a method and apparatus for streaming media to a plurality of adaptive client devices. In one aspect there is provided a method of providing a media stream over data channel of a best effort transmission network that includes a wireless path to a plurality of client devices. In another aspect there is provided a method of encoding a stream of data into chunks, whereby the chunks are obtained by determining a break point between them that corresponds to a silence point. In another aspect, there is provided a method for creating a library of encoded media for a media stream and linking the library to a plurality of cell phone devices.

A method and apparatus for remote laser-based detection of gas at levels exceeding natural background levels preferably utilizing wavelength modulated tunable diode laser absorption spectroscopy. In a preferred embodiment, background gas and noise are estimated using statistical moving average and variance calculations. Gas concentration length measurements resulting from the spectroscopy are preferably compared in real-time or near-real-time to the sum of the background and noise estimates and an alarm limit to detect gas presence of concern. Gas levels exceeding this detection threshold are preferably indicated by a prolonged output tone with a pitch indicative of the magnitude of the gas measurement, and gas levels below the detection threshold are preferably indicated by silence.

DTS Interactive provides low cost fully interactive immersive digital surround sound environment suitable for 3D gaming and other high fidelity audio applications, which can be configured to maintain compatibility with the existing infrastructure of Digital Surround Sound decoders. The component audio is stored and mixed in a compressed and simplified format that reduces memory requirements and processor utilization and increases the number of components that can be mixed without degrading audio quality. Techniques are also provided for “looping” compressed audio, which is an important and standard feature in gaming applications that manipulate PCM audio. In addition, decoder sync is ensured by transmitting frames of “silence” whenever mixed audio is not present either due to processing latency or the gaming application.

Discloses are systems and methods for detecting undesired call activity. Preferred embodiment systems and methods comprise detecting a call signal level, determining if the call signal level is below a predetermined silence level threshold, and measuring a duration the call signal level remains below the predetermined silence level threshold.

A system for providing statistical multiplexing of speech, other real-time data services and non-real-time data services for point to point and point to multipoint communications. The system has fast access and assignment procedures that allow the multiplexing of real-time, delay-critical data services with non-real-time data services. Continuity of periodic control channels across speech talkspurt and silence periods for conversational voice is maintained to carry signal measurement reports, channel quality feedback, and “comfort” noise information between different parts of the system.

A method and apparatus for conducting a transfer of a conference call are disclosed. A media gateway receives a message to transfer a conference call from a first call resource to a second call resource. If the message indicates a change in the number of clients participating in the conference call, the media gateway simultaneously transfers the conference call and plays a prompt to the clients indicating the change. If the message does not indicate the change, the media gateway transfers the conference call in response to detecting a period of silence.

In a speech training and recognition system, the current invention detects and warns the user about the similar sounding entries to vocabulary and permits entry of such confusingly similar terms which are marked along with the stored similar terms to identify the similar words. In addition, the states in similar words are weighted to apply more emphasis to the differences between similar words than the similarities of such words. Another aspect of the current invention is to use modified scoring algorithm to improve the recognition performance in the case where confusing entries were made to the vocabulary despite the warning. Yet another aspect of the current invention is to detect and warn the user about potential problems with new entries such as short words and two or more word entries with long silence periods in between words. Finally, the current invention also includes alerting the user about the dissimilarity of the multiple tokens of the same vocabulary item in the case of multiple-token training.

A method and apparatus for reducing the audible "clicks" or "pops" which occur when an ADPCM encoding and decoding system is employed in a communications system in which communication occurs over a dispersive channel. A novel technique is employed in which ADPCM-encoded silence is substituted for error-containing frames, and post-processing is performed on decoded frames while a muting window is open.

Disclosed are systems and methods which detect unauthorized, impermissible, or otherwise undesired call activity through a silence detection technique employing multiple samples. One embodiment monitors a call in progress to detect an event such as might be indicative of unauthorized call activity. Thereafter, a sampling process may be invoked which analyzes multiple samples of the call to make a determination as to whether or not a particular unauthorized call activity is being attempted. A party to the call may be muted to thereby prevent that party from thwarting the unauthorized call activity determination. Embodiments implement techniques for defeating parties to calls learning the unauthorized call activity detection system in order to avoid detection, such as by implementing a plurality of detection techniques.

An adaptive noise canceling system for extracting a desired signal, comprising an adaptive noise cancellation filtering circuit for suppressing noise from a first input signal using a second input signal as a reference signal, and generating an output filtered signal representing the desired signal; and an adaptive noise cancellation controller for receiving the first and second input signals and the output filtered signal, and generating an output control signal for controlling coefficients of at least one adaptive filter of the adaptive noise cancellation filtering circuit, comprising a silence detector unit for detecting whether an acoustical signal is present in the input signals and the output filtered signal, and generating a first output signal which indicates whether the acoustical signal is present; a signal detector unit for detecting whether the desired signal is present in the input signals and the output filtered signal, and generating a second output signal which indicates whether the desired signal is present; and an adaptive noise cancellation filter (ANCF) controller unit for receiving the first and second output signal to determine the characteristic of the input signals, and generating the output control signal which represents an updated coefficient parameter for updating the coefficients of the at least one adaptive filter of the adaptive noise cancellation filtering circuit.

A system and method enabling acoustic barge-in during a voice prompt in a communication system. An acoustic prompt model is trained to represent the system prompt using the specific speech signal of the prompt. The acoustic prompt model is utilized in a speech recognizer in parallel with the recognizer's active vocabulary words to suppress the echo of the prompt within the recognizer. The speech recognizer may also use a silence model and traditional garbage models such as noise models and out-of-vocabulary word models to reduce the likelihood that noises and out-of-vocabulary words in the user utterance will be mapped erroneously onto active vocabulary words.

A voice activity detector to analyze a short-term averaged energy (STAE), a long-term averaged energy (LTAE), and a peak-to-mean likelihood ratio (PMLR) in order to determine whether a current audio frame being transmitted represents voice or silence. This is accomplished by determining whether a sum of the STAE and a factor is greater than the LTAE. If not, the current audio frame represents silence. If so, a second set of determinations is performed. Herein, a determination is made as to whether the difference between the LTAE and the STAE is less than a predetermined threshold. If so, the current audio frame represents voice. Otherwise, the PMLR is determined and compared to a selected threshold. If the PMLR is greater than the selected threshold, the current audio frame represents a voice signal. Otherwise, it represents silence.

Noise is measured at one or more base stations in a mobile communication system during periodic silence periods. A periodic silence period is defined for at least one carrier that is independent of reverse link channel frame boundaries. The radio base stations transmits silence parameters defining the periodic silence period to mobile stations, which stop transmitting during the periodic silence periods. A time reference is provided to the mobile stations to synchronize the silence periods for all mobile stations.

Pitch detection of speech signals finds numerous applications in karaoke, voice recognition and scoring applications. While most of the existing techniques rely on time domain methods, the invention utilizes frequency domain methods. There is provided a method and system for determining the pitch of speech from a speech signal. The method includes the steps of: producing or obtaining the speech signal; distinguishing the speech signal into voiced, unvoiced or silence sections using speech signal energy levels; applying a Fourier Transform to the speech signal and obtaining speech signal parameters; determining peaks of the Fourier transformed speech signal; tracking the speech signal parameters of the determined peaks to select partials; and determining the pitch from the selected partials using a two-way mismatch error calculation.

The present invention is directed to voice communication devices in which an audio stream is divided into a sequence of individual packets, each of which is routed via pathways that can vary depending on the availability of network resources. All embodiments of the invention rely on an acoustic prioritization agent that assigns a priority value to the packets. The priority value is based on factors such as whether the packet contains voice activity and the degree of acoustic similarity between this packet and adjacent packets in the sequence. A confidence level, associated with the priority value, may also be assigned. In one embodiment, network congestion is reduced by deliberately failing to transmit packets that are judged to be acoustically similar to adjacent packets; the expectation is that, under these circumstances, traditional packet loss concealment algorithms in the receiving device will construct an acceptably accurate replica of the missing packet. In another embodiment, the receiving device can reduce the number of packets stored in its jitter buffer, and therefore the latency of the speech signal, by selectively deleting one or more packets within sustained silences or non-varying speech events. In both embodiments, the ability of the system to drop appropriate packets may be enhanced by taking into account the confidence levels associated with the priority assessments.

A system and method for location-dependent services for mobile stations using short range wireless technology such as Bluetooth. In an advantageous embodiment, the location-based service is a suggested profile change for a mobile station. A suggested profile may be a mode of operation for the mobile station's current location (e.g., silence in a meeting room) and may be accompanied by the period of time that the profile is valid and a timer value for a forced change to the suggested profile in the absence of user interaction. In response to a prompt from a mobile station that has received a suggested profile, a user may either accept or cancel the suggested profile. Various mechanisms are disclosed for ensuring that services such as a suggested profile change is sent to mobile stations having more than a passing association with the access point's coverage area.

A method and apparatus are provided for determining the quality of a speech transmission, including temporal clipping, delay and jitter, using a carefully constructed test signal (300) and digital signal processing techniques. The test signal that is to be transmitted through a speech transmission system (100) is created (700). Then the test signal is transmitted through the speech transmission system such that the speech transmission system creates an output signal that corresponds to the input signal, as modified by the speech transmission system (702). The test signal includes multiple segments (500) of speech signals interleaved with periods of silence. The periods of silence vary in duration according to a predefined pattern. Each segment of speech signals includes multiple predefined speech samples or symbols (400, 402, 404, 406, 408, 410, 412, 414) interleaved with a plurality of silence gaps. The speech samples have a common period of duration, but the silence gaps do not. The output signal from the speech transmission system is preferably recorded (704) and analyzed to determine its quality, including temporal clipping (706). This analysis preferably includes comparing the output signal with a reference signal derived from the test signal using a cross correlation function. A processor (114) coupled to memory (116) records and analyzes the output signal.

A system and method enabling acoustic barge-in during a voice prompt in a communication system. An acoustic prompt model is trained to represent the system prompt using the specific speech signal of the prompt. The acoustic prompt model is utilized in a speech recognizer in parallel with the recognizer's active vocabulary words to suppress the echo of the prompt within the recognizer. The speech recognizer may also use a silence model and traditional garbage models such as noise models and out-of-vocabulary word models to reduce the likelihood that noises and out-of-vocabulary words in the user utterance will be mapped erroneously onto active vocabulary words.

Devices, software and methods are provided for generating aggregate comfort noise for teleconferencing over IP networks. A transcoding component includes a decoder for decoding streams of packets. A summing component has a summer with summing inputs to receive the decoded streams of packets. The summing component has at least one silence flag input, and an additional signaling path is used by the transcoding component to signal to the silence flag input if any of the decoded streams of packets includes a silence identification packet. In another embodiment, the summing component may or may not include the silence flag input, but the device includes an aggregate comfort noise generation component. The aggregate comfort noise may be programmed to be a balanced representation of all background noises.