Abstract: A breathing mask adapted to be placed over a wearer's face, comprises a mask body including a gas inlet port to be disposed in flow communication with the wearer's breathing passage for flow of a gas in a predetermined flow stream there through upon inhalation by the wearer; a communications microphone (30) mounted to said mask body to capture the voice of the wearer, said communications microphone generating sound signals; an attenuation device (34) for attenuating said sound signals; a sound monitor (36) for monitoring the intensity of sound near the communications microphone in a predetermined frequency range, connected to a controller device (38) for activating the attenuation device when the sound intensity monitored by the sound monitor is in a predetermined level range.

Abstract: One embodiment of the invention is a computer controlled method for use with a communication system. The method includes a step of receiving a plurality of communications, where each one of the plurality of communications is from one of a plurality of communication sources; includes a step of mixing (that is responsive to a plurality of floor controls) the plurality of communications for a plurality of outputs associated with plurality of communication sources; and includes a step of analyzing, for a plurality of users associated with the plurality of communication sources, one or more conversational characteristics of two or more of the plurality of users. The method also includes a step of automatically adjusting the plurality of floor controls responsive to the step of analyzing. Other embodiments include systems and devices that use the method as well as program products that cause a computer to execute the method.

Abstract: A method and apparatus for dynamically enabling the activation and deactivation of comfort noise over a VoIP media path or channel are disclosed. The present method detects all sound levels in the media path and only activates the comfort noise in the absence of sound and when the background noise level or the telephone line noise level is low rather than only in the absence of speech.

Abstract: The present invention is a system and method that improves upon voice activity detection by packetizing actual noise signals, typically background noise. In accordance with the present invention an access network receives an input voice signal (including noise) and converts the input voice signal into a packetized voice signal. The packetized voice signal is transmitted via a network to an egress network. The egress network receives the packetized voice signal, converts the packetized voice signal into an output voice signal, and outputs the output voice signal. The egress network also extracts and stores noise packets from the received packetized voice signal and converts the packetized noise signal into an output noise signal. When the access network ceases to receive the input voice signal while the call is still ongoing, the access network instructs the egress network to continually output the output noise signal.

Abstract: A method, system and computer readable device for recognizing a partial utterance in an automatic speech recognition (ASR) system where said method comprising the steps of, receiving, by a ASR recognition unit, an input signal representing a speech utterance or word and transcribing the input signal into text, interpreting, by a ASR interpreter unit, whether the text is either a positive or a negative match to a list of automated options by matching the text with a grammar or semantic database representing the list of automated options, wherein if the ASR interpreter unit results in said positive match proceeding to a next input signal and if the ASR interpreter unit results in said negative match rejecting the text as representing said partial utterance, and processing, by a linguistic filtering unit, the rejected text to derive a correct match between the rejected text and the grammar or semantic database.

Abstract: One aspect of the invention is a method of using a computer to identify a conversation. Another aspect is a method for an audio processing system that identifies conversations and enhances each conversation for each user in the conversation.

Abstract: Precision piecewise polynomial approximation for Ephraim-Malah filter is described herein. In one embodiment, an exemplary process includes computing a first parameter based on Wiener filter weights and posterior signal-to-noise (SNR) via a polynomial approximation mechanism without using a mathematical division operation, and generating Ephrain-Malah filter coefficients based on the first parameter. Other methods and apparatuses are also described.

Abstract: The present invention is a method and apparatus in a data processing system that includes a Voice over Internet Protocol (VoIP) communication system for improving transmit and receive data paths. The communication system includes a digital signal processing unit. The digital signal processing unit includes a mandatory coder/decoder (codec) that does not include an internal packet loss concealment (PLC) function, an internal voice activity detection (VAD) function, an internal comfort noise generation (CNG) function, or an internal discontinuous transmission generation (DTX) function. The digital signal processing unit also includes an enhanced codec that includes any combination of the following modules all internal to the enhanced codec: internal packet loss concealment (PLC) function, a voice activity detection (VAD) function, a comfort noise generation (CNG) function, and a discontinuous transmission generation (DTX) function.

Abstract: Differential dynamic content delivery including providing a session document for a presentation, wherein the session document includes a session grammar and a session structured document; selecting from the session structured document a classified structural element in dependence upon user classifications of a user participant in the presentation; presenting the selected structural element to the user; streaming presentation speech to the user including individual speech from at least one user participating in the presentation; converting the presentation speech to text; detecting whether the presentation speech contains simultaneous individual speech from two or more users; and displaying the text if the presentation speech contains simultaneous individual speech from two or more users.

Abstract: A method and system for controlling potentially harmful signals in a signal arranged to convey speech is described. The method includes the steps of establishing characteristics of the signal when it is conveying speech; monitoring the signal; and controlling the signal relative to the established characteristics.

Abstract: Techniques for implementing vocoders in parallel digital signal processors are described. A preferred approach is implemented in conjunction with the BOPS® Manifold Array (ManArray™) processing architecture so that in an array of N parallel processing elements, N channels of voice communication are processed in parallel. Techniques for forcing vocoder processing of one data-frame to take the same number of cycles are described. Improved throughput and lower clock rates can be achieved.

Abstract: This disclosure is directed to techniques for condensed voice buffering, transmission and playback. The techniques may involve identification of encoded voice frames as either speech or a pause, and selective exclusion of a portion of the frames for storage, transmission or playback based on the identification. In this manner, the techniques are capable of condensing a series of encoded voice frames. When variable rate coding is employed, a pause frame may be identified, for example, based on a threshold comparison for the rate of the encoded frame. In some cases, the techniques may involve excluding only a portion of the identified frames from a consecutive sequence of the identified frames, thereby preserving a minimum number of the identified frames needed for intelligible conversation.

Abstract: A system and method for noise cancellation with noise ramp tracking in the presence of severe or ramping acoustic noise. The system conducts an estimation of the noise level in the input signal and modifies the signal based upon this noise estimate. A windowed Fourier transform is performed upon the input speech signal and an estimation of a histogram of the frequency magnitudes of the noise level and other related parameters is generated and used to compute a spectral gain function that is applied to components of the Fourier transform of the input speech signal. The enhanced components of the Fourier transform are processed by an inverse Fourier transform in order to reconstruct a noise reduced speech signal.

Abstract: A system and method for detecting cell phone noise induced in telecommunication equipment, especially in microphones and other unshielded electronic units connected to a communication terminal. A noise detector is configured to execute a so-called “cepstrum” transform of a captured signal exposed to cell phone noise. Due to the characteristics of cell phone radio signals using TDMA, cell phone induced can then easily be detected from the cepstrum transform as peaks at known samples, and noise elimination or attenuation may then be executed on the captured signal when cell phone noise is detected.

Abstract: A method for improving the quality of a speech signal extracted from a noisy acoustic environment is provided. In one approach, a signal separation process is associated with a voice activity detector. The voice activity detector is a two-channel detector, which enables a particularly robust and accurate detection of voice activity. When speech is detected, the voice activity detector generates a control signal. The control signal is used to activate, adjust, or control signal separation processes or post-processing operations to improve the quality of the resulting speech signal. In another approach, a signal separation process is provided as a learning stage and an output stage. The learning stage aggressively adjusts to current acoustic conditions, and passes coefficients to the output stage. The output stage adapts more slowly, and generates a speech-content signal and a noise dominant signal.

Abstract: A method and detector for providing a noise resistant utterance detector is provided by extracting a noise estimate (15) to augment the signal-to-noise ratio of the speech signal, inverse filtering (17) of the speech signal to focus on the periodic excitation part of the signal and spectral reshaping (19) to accentuate separation between formants.

Abstract: An embodiment may include an apparatus comprising a dejitter buffer to receive packets containing audio data, a codec coupled with the dejitter buffer, the codec to receive coded audio frames from the dejitter buffer and decode them, and a concealed seconds meter coupled with the dejitter buffer, the concealed seconds meter to record concealment events by the decoder to provide an objective measure of media impairment. Another exemplary embodiment may be a method comprising receiving packets containing audio information at a dejitter buffer, decomposing the packets to coded audio frames, sending the coded audio frames to a decoder and decoding the frames, generating a concealment output stream if the decoder does not receive a valid frame from the dejitter buffer, and recording concealment events to provide an objective measure of media impairment.

Abstract: An audio classification system classifies sounds in an audio stream as belonging to one of a relatively small number of classes. The audio classification system includes a signal analysis component [301] and a decoder [302]. The decoder [302] includes a number of models [310-316] for performing the audio classifications. In one implementation, the possible classifications include: vowels, fricatives, narrowband, wideband, coughing, gender, and silence. The classified audio may be used to enhance speech recognition of the audio stream.

Abstract: A “speech onset detector” provides a variable length frame buffer in combination with either variable transmission rate or temporal speech compression for buffered signal frames. The variable length buffer buffers frames that are not clearly identified as either speech or non-speech frames during an initial analysis. Buffering of signal frames continues until a current frame is identified as either speech or non-speech. If the current frame is identified as non-speech, buffered frames are encoded as non-speech frames. However, if the current frame is identified as a speech frame, buffered frames are searched for the actual onset point of the speech. Once that onset point is identified, the signal is either transmitted in a burst, or a time-scale modification of the buffered signal is applied for compressing buffered frames beginning with the frame in which onset point is detected. The compressed frames are then encoded as one or more speech frames.

Abstract: Techniques utilising Time Scale Modification (TSM) of signals are described. The signal is analysed and divided into frames of similar signal types. Techniques specific to the signal type are then applied to the frames thereby optimising the modification process. The method of the present invention enables TSM of different audio signal parts to be realized using different methods, and a system for effecting said method is also described.

Abstract: Recordings of broadcast audio content often contain errors (e.g., noise, signal loss, interference, talkover). A method and apparatus are provided for improving the quality of such a recording. Multiple recordings of a broadcast audio program are identified, and are aligned according to some time index of the program, such as the beginning, midpoint or end of one of the recordings. Samples of each recording are taken and compared. If a majority (or plurality) of the samples agree (e.g., they match within an allowable threshold of variance), one of them is used to generate or populate a new recording. If there is no majority (or plurality), one of the samples may be chosen at random, on the basis of which recording has most often been in the majority (or plurality), or on some other basis. Or, the method may be repeated or extended to obtain samples of other recordings.

Abstract: 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.

Abstract: Estimating a signal power in a compressed audio signal [A] is provided, the audio signal comprising blocks of quantized samples, a given block being provided with a set of scale factors. The estimating is performed by extracting the set of scale factors from the compressed audio signal, and estimating the signal power in the given block based on a combination of the scale factors. Advantageously, the extracting step and estimating step are performed on only a sub-set of the set of scale factors. The signal power estimation may be used in a silence detector (11) for use in a receiver (1).

Abstract: Speech encoders and methods of speech encoding are disclosed that encode inactive frames at different rates. Apparatus and methods for processing an encoded speech signal are disclosed that calculate a decoded frame based on a description of a spectral envelope over a first frequency band and the description of a spectral envelope over a second frequency band, in which the description for the first frequency band is based on information from a corresponding encoded frame and the description for the second frequency band is based on information from at least one preceding encoded frame. Calculation of the decoded frame may also be based on a description of temporal information for the second frequency band that is based on information from at least one preceding encoded frame.

Abstract: Disclosed configurations include systems, methods, and apparatus arranged to generate a sequence of spectral tilt values that is based on inactive frames of a speech signal. For each of a plurality of inactive frames of the speech signal, a transmit decision is made according to a change calculated among at least two corresponding values of the sequence. The outcome of the transmit decision determines whether a silence description is transmitted for the corresponding inactive frame.

Abstract: Method and apparatus detect voice activity for spectrum or power efficiency purposes. The method determines and tracks the instant, minimum and maximum power levels of the input signal. The method selects a first range of signals to be considered as noise, and a second range of signals to be considered as voice. The method uses the selected voice, noise and power levels to calculate a log likelihood ratio (LLR). The method uses the LLR to determine a threshold, then uses the threshold for differentiating between noise and voice.

Abstract: The present invention discloses an audio signal segmentation algorithm comprising the following steps. First, an audio signal is provided. Then, an audio activity detection (AAD) step is applied to divide the audio signal into at least one noise segment and at least one noisy audio segment. Then, an audio feature extraction step is used on the noisy audio segment to obtain multiple audio features. Then, a smoothing step is applied. Then, multiple speech frames and multiple music frames are discriminated. The speech frames and the music frames compose at least one speech segment and at least one music segment. Finally, the speech segment and the music segment are segmented from the noisy audio segment.

Abstract: The method of identifying excess noise in a computer system includes first recording a silence sample; second recording an isolated noise sample while operating a computer system component in isolation from other computer system components; comparing signal characteristics of the silence sample with signal characteristics of the isolated noise sample; and, attributing the isolated noise sample to the isolated computer component when the signal characteristics of the silence sample differ by a preset threshold from the signal characteristics of the isolated noise sample. The inventive method can further include logging the signal characteristics of the silence sample and the isolated noise sample; reporting excess noise identified in the identifying step; and, suggesting a remedy for the identified excess noise.

Abstract: The present invention is a system and method that improves upon voice activity detection by packetizing actual noise signals, typically background noise. In accordance with the present invention an access network receives an input voice signal (including noise) and converts the input voice signal into a packetized voice signal. The packetized voice signal is transmitted via a network to an egress network. The egress network receives the packetized voice signal, converts the packetized voice signal into an output voice signal, and outputs the output voice signal. The egress network also extracts and stores noise packets from the received packetized voice signal and converts the packetized noise signal into an output noise signal. When the access network ceases to receive the input voice signal while the call is still ongoing, the access network instructs the egress network to continually output the output noise signal.

Abstract: A system and method for voice transmission over high level network protocols. On the Internet and the World Wide Web, such high level protocols are HTTP/TCP. The restrictions imposed by firewalls and proxy servers are avoided by using HTTP level connections to transmit voice data. In addition, packet delivery guarantees are obtained by using TCP instead of UDP. Variable compression based on silence detection takes advantage of the natural silences and pauses in human speech, thus reducing the delays in transmission caused by using HTTP/TCP. The silence detection includes the ability to bookend the voice data sent with small portions of silence to insure that the voice sounds natural. Finally, the voice data is transmitted to each client computer, independently from a common circular list of voice data, thus insuring that all clients will stay current with the most recent voice data. The combination of these features enables simple, seamless, and interactive Internet conferencing.

Abstract: The present invention is a system and method for packetizing actual noise signals, typically background noise, received by an access gateway from a speaking party and transmitting these packetized noise signals via a network to an egress gateway. The egress gateway converts the packetized noise signal into noise signals suitable for output and transmits the output noise signals to a listening party. When the access gateway detects that no voice signal is being received and only a noise signal is being received for a predetermined period of time, the access gateway instructs the egress network to continually transmit output noise signals to the listening party and ceases to transmit packetized noise signals to the egress gateway.

Abstract: An input signal is input via an input part. A plurality of signal section candidate detecting parts having different detection algorithms detect an intended signal section candidate and a noise signal section candidate from the input signal. A signal section classifying part is notified of detection results from the respective signal section candidate detecting parts, and classifies the respective signal section candidates based on a combination of the detection results.

Abstract: A method and apparatus for finding endpoints in speech by utilizing information contained in speech prosody. Prosody denotes the way speakers modulate the timing, pitch and loudness of phones, words, and phrases to convey certain aspects of meaning; informally, prosody includes what is perceived as the “rhythm” and “melody” of speech. Because speakers use prosody to convey units of speech to listeners, the method and apparatus performs endpoint detection by extracting and interpreting the relevant prosodic properties of speech.

Abstract: The present invention relates to a mobile set integrating a memory efficient data storage system for the real time recording of voice conversations, data transmission and the like. The data recorder has the capacity to selectively choose the most relevant time frames of a conversation for recording, while discarding time frames that only occupy additional space in memory without holding any conversational data. The invention executes a series of logic steps on each signal including a voice activity detector step, frame comparison step, and sequential recording step. A mobile set having a modified architecture for performing the methods of the present invention is also disclosed.

Abstract: Speech coding systems include multi-rate speech codecs having an encoder and a decoder. Silence description coding for multi-rate speech coding systems that employ discontinued transmission is performed in either the encoder or the decoder of the multi-rate speech codec. It may also be performed in a distributed manner wherein it is performed partially in the encoder and partially in the decoder. The silence description coding is performed on a speech signal having a substantially non-speech-like characteristic. Voice activity detection classifies the speech signal as being either substantially speech-like or substantially non-speech-like. The silence description coding is selected from a plurality of coding modes. In certain embodiments of the invention, the silence description coding is a source coding mode that operates at a bit rate that fits within a bit rate budget as determined by all of the available source coding modes within the plurality of coding modes.

Abstract: A first CN code (silence code) obtained by encoding a silence signal, which is contained in an input signal, by a silence compression function of a first speech encoding scheme is transcoded to a second CN code of a second speech encoding scheme without decoding the first CN code to a CN signal. For example, the first CN code is demultiplexed into a plurality of first element codes by a code demultiplexer, the first element codes are each transcoded to a plurality of second element codes that constitute the second CN code, and the second element codes obtained by this transcoding are multiplexed to output the second CN code.

Abstract: A device and a method for speech analysis are provided, comprising measuring fundamental notes of a speech sequence to be analysed and identifying frequency intervals between at least some of said fundamental notes. An assessment is then made as to the frequency at which at least some of these thus identified intervals occur in the speech sequence to be analysed. Among other applications are speech training and diagnosis of pathological conditions.

Abstract: An apparatus and a method for computing a Speech Absence Probability (SAP), and an apparatus and a method for removing noise by using the SAP computing device and method are provided.

Abstract: Problems of front-end clipping and excessively long holdover times in digitally encoded speech are resolved by the introduction of a queue at the transmitting end of a digital conversation. Samples are transmitted from the queue until an interval of low energy samples is encountered upon which time samples are not transmitted from queue until energy samples are present.

Abstract: In a distributed voice recognition system, a back-end pattern matching unit 27 can be informed of voice activity detection information as developed through use of a back-end voice activity detector 25. Although no specific voice activity detection information is developed or forwarded by the front-end of the system, precursor information as developed at the back-end can be used by the voice activity detector to nevertheless ascertain with relative accuracy the presence or absence of voice in a given set of corresponding voice recognition features as developed by the front-end of the system.

Abstract: The invention concerns a method for detecting voice activity in a digital speech signal, in at least a frequency band, for example by means of a detecting automaton whereof the status is controlled on the basis of an energy analysis of the signal. The control of said automaton, or more generally the determination of voice activity, comprises a comparison, in the frequency band, of two different versions of the speech signal one of which at least is a noise-corrected version.

Abstract: To address the need for reducing audio overhang in wireless communication systems (e.g., 100), the present invention provides for the deletion of silent frames before they are converted to audio by the listening devices. The present invention only provides for the deletion of a portion of the silent frames that make up a period of silence or low voice activity in the speaker's audio. Voice frames that make up periods of silence less than a given length of time are not deleted.

Abstract: An utterance detector for speech recognition is described. The detector consists of two components. The first part makes a speech/non-speech decision for each incoming speech frame. The decision is based on a frequency-selective autocorrelation function obtained by speech power spectrum estimation, frequency filter, and inverse Fourier transform. The second component makes utterance detection decision, using a state machine that describes the detection process in terms of the speech/non-speech decision made by the first component.

Abstract: A technique for separating an acoustic signal into a voiced (V) component corresponding to an electrolaryngeal source and an unvoiced (U) component corresponding to a turbulence source. The technique can be used to improve the quality of electrolaryngeal speech, and may be adapted for use in a special purpose telephone. A method according to the invention extracts a segment of consecutive values from the original stream of numerical values, and performs a discrete Fourier transform on the this first group of values. Next, a second group of values is extracted from components of the discrete Fourier transform result which correspond to an electrolaryngeal fixed repetition rate, F0, and harmonics thereof. An inverse-Fourier transform is applied to the second group of values, to produce a representation of a segment of the V component. Multiple V component segments are then concatenated to form a V component sample stream.

Abstract: A method for detecting pauses in speech signals is disclosed in which the frequency spectrum is divided into two or more sub-bands. Samples of the signals on the sub-bands are stored at intervals, the energy levels of the sub-bands are determined on the basis of the stored samples, a power threshold value (thr) is determined, and the energy levels of the sub-bands are compared with said power threshold value (thr). A subband minimum is set and a detection time limit is set so that, in a noise situation, a speech pause can be verified by checking to determine if each pause detected remains for the duration of the detection time limit and if a pause is detected in at least said minimum subbands.

Abstract: Packetized CELP-encoded speech playout with frame truncation only during silence and frame expansion method dependent upon voicing classification with voiced frame expansion maintaining phase alignment.

Abstract: With respect to data having periodicity to be compressed, windows of the same size are set for every two sections according to an interval of peaks appearing substantially periodically and processing for sorting sample data alternately among the set windows of the same size is sequentially performed, whereby a frequency of data having periodicity is replaced with an approximately half frequency without damaging reproducibility to original data at all to make it possible to apply compression processing to data of the replaced low frequency. If this sorting processing is applied to compression processing having a characteristic that a compression ratio is not increased in a high-frequency region, it becomes possible to improve a compression ratio without damaging a quality of reproduced data by decompression at all.

Abstract: Method and system for delivering a message over a telecommunications network to a recipient comprising transmitting a message over the telecommunications network to the recipient when a predetermined energy/silence condition is detected, performing echo cancellation on a signal communicated from the telecommunications network, and monitoring the signal to detect the energy/silence condition.

Abstract: A method and apparatus for performing real-time endpoint detection for use in automatic speech recognition. A filter is applied to the input speech signal and the filter output is then evaluated with use of a state transition diagram (i.e., a finite state machine). The filter is advantageously designed in light of several criteria in order to increase the accuracy and robustness of detection. The state transition diagram advantageously has three states. The endpoints which are detected may then be advantageously applied to the problem of energy normalization of the speech portion of the signal.

Abstract: An apparatus is provided for detecting the presence of speech within an input speech signal. Speech is detected by treating the average frame energy of an input speech signal as a sampled signal and looking for modulations within the sampled signal that are characteristic of speech.