Abstract: A method and apparatus are provided for generating comfort noise in a communication device. The method includes receiving a signal, scaling the signal to a preselected value, indicating whether an error occurred during transmission of the signal, and providing the scaled signal as an output signal in response to receiving the indication that the error occurred during transmission. The apparatus includes a scaler for receiving a signal and being capable of scaling the signal to a preselected value. The apparatus includes an indicator capable of indicating that an error occurred during transmission of the signal, wherein the scaled signal is provided as an output signal in response to an indication that the error occurred during transmission.

Abstract: A method and system for providing comfort noise in the non-speech periods in speech communication. The comfort noise is generated based on whether the background noise in the speech input is stationary or non-stationary. If the background noise is non-stationary, a random component is inserted in the comfort noise using a dithering process. If the background noise is stationary, the dithering process is not used.

Abstract: A subset of values is used to discriminate voice activity in a signal. The subset of values belongs to a larger set of values representing a segment of a signal, the larger set of values being suitable for speech recognition.

Abstract: A source signal (e.g. a speech sample) is processed or transmitted by a speech coder 1 and converted into a reception signal (coded speech signal). The source and reception signals are separately subjected to preprocessing 2 and psychoacoustic modelling 3. This is followed by a distance calculation 4, which assesses the similarity of the signals. Lastly, an MOS calculation is carried out in order to obtain a result comparable with human evaluation. According to the invention, in order to assess the transmission quality a spectral similarity value is determined which is based on calculation of the covariance of the spectra of the source signal and reception signal and division of the covariance by the standard deviations of the two said spectra. The method makes it possible to obtain an objective assessment (speech quality prediction) while taking the human auditory process into account.

Abstract: A method for reducing interference in acoustic signals by using of an adaptive filter method involving spectral subtraction. The inventive method enables a significant reduction of interference in acoustic signals, especially voice signals, without causing any substantial falsification of said signals such as echo or musical tones, and significantly reduces computational requirements in comparison with other methods known per se that are similarly designed to improve signal quality.

Abstract: A speech coding method and device for encoding and decoding an input signal and providing synthesized speech, wherein the higher frequency components of the synthesized speech are achieved by high-pass filtering and coloring an artificial signal to provide a processed artificial signal. The processed artificial signal is scaled by a first scaling factor during the active speech periods of the input signal and a second scaling factor during the non-active speech periods, wherein the first scaling factor is characteristic of the higher frequency band of the input signal and the second scaling factor is characteristic of the lower frequency band of the input signal. In particular, the second scaling factor is estimated based on the lower frequency components of the synthesized speech and the coloring of the artificial signal is based on the linear predictive coding coefficients characteristic of the lower frequency of the input signal.

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: A method for determining points of change or novelty in an audio signal measures the self similarity of components of the audio signal. For each time window in an audio signal, a formula is used to determine a vector parameterization value. The self-similarity as well as cross-similarity between each of the parameterization values is then determined for all past and future window regions. A significant point of novelty or change will have a high self-similarity in the past and future, and a low cross-similarity. The extent of the time difference between “past” and “future” can be varied to change the scale of the system so that, for example, individual musical notes can be found using a short time extent while longer events, such as musical themes or changing of speakers, can be identified by considering windows further into the past or future. The result is a measure of the degree of change, or how novel the source audio is at any time.

Abstract: A method and apparatus for detecting silence in voice packets. A packet energy calculator calculates a smoothed energy value for each packet of voice data to be transmitted. A noise level detector adaptively calculates noise values during periods of said silence. A silent packet detector compares the energy value to the noise value and if it is less than the noise value and less than a predetermined silence ceiling value then silence is indicated. Also, if the energy value is less than a predetermined silence noise value then silence is also indicated.

Abstract: Such methods are indispensable to ensure natural voice transmission from noisy environments, such as airports or sports arenas, by means of mobile or fixed communications terminals. Noise reduction is also necessary in voice-controlled apparatus to improve the quality of voice recognition. Using a Wiener filter in the well-known spectral subtraction method for noise reduction as well as a compressor and an expander, the dynamic range of the spectral subtraction is extended considerably. By nonlinear control of the overestimation factor and the noise floor of the transfer function of the Wiener filter, in comparison with the known prior art, a qualitative improvement in speech intelligibility is achieved for widely different ratios of speech to noise.

Abstract: A system and method for removing noise from a signal containing speech (or a related, information carrying signal) and noise. A speech or voice activity detector (VAD) is provided for detecting whether speech signals are present in individual time frames of an input signal. The VAD comprises a speech detector that receives as input the input signal and examines the input signal in order to generate a plurality of statistics that represent characteristics indicative of the presence or absence of speech in a time frame of the input signal, and generates an output based on the plurality of statistics representing a likelihood of speech presence in a current time frame; and a state machine coupled to the speech detector and having a plurality of states. The state machine receives as input the output of the speech detector and transitions between the plurality of states based on a state at a previous time frame and the output of the speech detector for the current time frame.

Abstract: A noise suppression device receives data representative of a noise-corrupted signal which contains a speech signal and a noise signal, divides the received data into data frames, and then passes the data frames through a pre-filter to remove a dc-component and the minimum phase aspect of the noise-corrupted signal. The noise suppression device appends adjacent data frames to eliminate boundary discontinuities, and applies fast Fourier transform to the appended data frames. A voice activity detector of the noise suppression device determines if the noise-corrupted signal contains the speech signal based on components in the time domain and the frequency domain. A smoothed Wiener filter of the noise suppression device filters the data frames in the frequency domain using different sizes of a window based on the existence of the speech signal. Filter coefficients used for Wiener filter are smoothed before filtering.

Abstract: The decoder receives a bit stream representative of an audio signal, with a flag indicating any missing frames. For each frame, an excitation signal is formed from excitation parameters recovered in the bit stream if the frame is valid and estimated otherwise if the frame is missing, and the excitation signal is filtered by means of a synthesis filter to obtain a decoded audio signal. A linear prediction analysis is performed on the basis of the decoded audio signal obtained up to the preceding frame to estimate at least in part a synthesis filter relating to the current frame, whereby the successive synthesis filters used to filter the excitation signal, as long as there is no missing frame, conform to the estimated synthesis filters.

Abstract: The first codec-based dummy string generator 132 generates a first codec-based dummy string in a first code string conforming to a first format based on the first coding method. The second codec encoder 131 generates a second code string having been encoded with a higher efficiency than the first code string and conforming to a second format different from the first format. The code string generator 133 generates a synthetic code string by embedding the second codec-based code string generated by the second codec encode block 131 in a blank area formed in the first code string based on the first codec-based dummy string generated by the first code dummy string generator 132.

Abstract: A system and method employing an access terminal for maintaining discontinuous communications including a gateway receiver for receiving the discontinuous information, a radio frequency (RF) communication link via geosynchronous earth orbit satellite for conveying multiple communication channels using time division multiple access (TDMA), the access terminal initiating information communication with the receiver via at least one of the multiple communication channels. The access terminal further includes a memory for storing protocol processing information and a transmitter for establishing the radio frequency communication link to the receiver of the terrestrial gateway system. The access terminal memory provides for destroying of a signal pattern or protocol assigned to the access terminal by the gateway receiver or transmission of keep-alive bursts by the transmitter during periods of inactivity to maintain information communication with the receiver.

Abstract: Speech transmission method by initializing silence, transmit, and blank-period counters; receiving frame; determining frame is speech; if transmit counter is zero and blank-period counter is less than x then discard frame, increment blank-period counter, and return to second step; if transmit counter is zero, blank-period counter greater than x−1, and frame not speech then discard frame, increment blank-period counter, and return to second step; if transmit counter is zero, blank-period counter greater than x−1, and frame is speech then set transmit counter to one, set blank-period counter to zero, set silence counter to zero, encode frame, transmit encoded frame, and return to second step; if transmit counter is one, frame not speech, and silence counter less than y then encode frame, transmit encoded frame, increment silence counter, and return to second step; if transmit counter is one, frame not speech, and silence counter greater than y+z−2 then set transmit counter to zero, discar

Abstract: Herein disclosed is a sound signal encoding apparatus, comprises: sampling means for dividing and sampling a signal inputted therein into a plurality of sound signal sections based on the frequency ranges of the sound signal; each of the sound sections having a pure sound component and a non-pure sound component, and encoding means for encoding the sound signal sections after quantizing the sound signal sections divided and sampled based on the frequency ranges of the sound signal The encoding means comprises a deciding unit for deciding which one in the pure sound component and non-pure sound component is more than the other of the pure sound component and non-pure sound component with respect to each of the sound signal sections divided and sampled based on the frequency ranges of the sound signal; a fast quantizing unit for quantizing only the pure sound component at a first quantization level when the deciding unit is operated to decide that the pure sound component is more than the non-pure sound compone

Abstract: When a delivered speed of a listening speech (speech speed) is slowed down, a connection order generator (8) always monitors a data length of input speech, an output data length calculated previously by a conversion function concerning a preset scaling factor, and a data length of actual output speech in predetermined processing unit, then decides connection order not to cause inconsistency among them. The speech data and the connection data are connected without omission of speech information by controlling a speech data connector (9). When power of an input signal data is calculated to discriminate a speech interval and a non-speech interval, a threshold value for power is decided according to a maximum value of the power and difference between the maximum value and a minimum value.

Abstract: Silence description coding for multi-rate speech coding systems that employ discontinued transmission. Speech coding systems include multi-rate speech codecs having an encoder and a decoder. The silence description coding 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 method and apparatus for eighth-rate random number generation for speech coders includes a random number generator configured to generate values of a first random variable. A lookup table is used to store values of a second random variable. The lookup table is addressed with the values of the first random variable. The second random variable is an inverse transform of a cumulative distribution function of the first random variable. An codec encodes input silence frames with the values of the first and second random variables, and regenerates the silence frames with the values of the first and second random variables. The speech coder may be an enhanced variable rate coder, and the silence frames may be encoded at eighth rate. The random variables are advantageously Gaussian random variables with values that are uniformly distributed between zero and one.

Abstract: Making use of a digital acoustic signal processing apparatus arranged by employing memory device for storing a digital acoustic signal, acoustic frequency feature enhancing device for enhancing an acoustic frequency feature, and low-speed sound reproducing device for changing a speed of the stored voice to reproduce this voice as a low speed into a hearing aid and an appliance with an acoustic output, a hearing function difficulty due to an age is aided in utilization of audio output appliances such as a hearing aid, television receiver, and a telephone receiver. After the voice has been stored in the memory device, a process for enhancing the frequency characteristic in order to fit the frequency characteristic to the individual hearing characteristic and the voice reproducing environment is carried out and thereafter represented to the user. The user can repeatedly listen the voice stored in the memory device with employment of control device for controlling the voice reproducing operation.

Abstract: A human speech detection method detects pure-speech signals in an audio signal containing a mixture of pure-speech and non-speech or mixed-speech signals. The method accurately detects the pure-speech signals by computing a novel Valley Percentage feature from the audio signal and then classifying the audio signals into pure-speech and non-speech (or mixed-speech) classifications. The Valley Percentage is a measurement of the low energy parts of the audio signal (the valley) in comparison to the high energy parts of the audio signal (the mountain). To classify the audio signal, the method performs a threshold decision on the value of the Valley Percentage. Using a binary mask, a high Valley Percentage is classified as pure-speech and a low Valley Percentage is classified as non-speech (or mixed-speech). The method further employs morphological filters to improve the accuracy of human speech detection.

Abstract: A voice encoder using a VOX (voice operated transmission) control has a pitch analyzer and a high-efficiency encoder. When a voiced state is detected in an input audio signal, the input audio signal and pitch information extracted therefrom are encoded by the high-efficiency encoder and transmitted to a voice decoder. When an unvoiced state is detected, the high-efficiency encoder encodes the input audio signal without a gain of the pitch information. The encoded data without using the gain information is transmitted after a post-amble signal to obtain natural background noise.

Abstract: The invention relates to an improved adaptive spectral estimator for estimating the spectral components in a signal containing both an information signal, such as speech, and noise. A method and system provide for generating noise estimates and then only updating the noise estimates during pauses in an information signal, when speech or other information is not detected, rather than continuously updating the noise estimates. A noise estimate is calculated for each frequency band and provides for the inclusion of a variable mathematical factor that can be set by the user to produce the best sound quality.

Abstract: The present invention relates to the management of voice data.Voice messages left on a recipient's answerphone or delivered via a voicemail system are a popular form of person-to-person communication. Such voice messages are quick to generate for the sender but are relatively difficult to review for the recipient; speech is slow to listen to and, unlike inherently visual forms of messages such as electronic mail or handwritten notes, cannot be quickly scanned for the relevant information. The present invention aims to make it easier for users to find relevant information in voice messages, and other kinds of voice record, such as recordings of meetings and recorded dictation.According to the present invention we provide a method of speech segmentation comprising processing speech data so as to detect putative pauses and characterised by forming speech block boundaries at a selected subset of the pauses, said selection being based on a preselected target speech block length.

Abstract: A silence compression system that improves data compression in a digital speech storage device, such as a digital telephone answering machine, without undue clipping of voice signals. Instead of employing only real-time compression, the inventive silence system analyzes and compresses or re-compresses digital speech samples stored previously, when the voice messaging system is off-line or otherwise in a low priority state. A method of silence compression comprises receiving real-time speech samples, storing the same in memory, and analyzing the stored speech samples at a later time to determine thresholds for periods of silence. The periods of silence are then compressed, and the silence compressed voice message is restored in memory. In this fashion, the processor is not required to make a silence period determination on-the-fly simultaneous with encoding and compression of the real-time voice message, and thus is not subjected to heavy processor loads typically encountered in real time.

Abstract: A signal communication apparatus and method enables direct communication between communication systems of the silence compression and the non-silence compression type. The transmission and reception can each discriminate whether an audio signal is in a sound-present period or in a sound-absent period and this discrimination is output as period identification data. The audio signal is encoded, and the encoded data is selected and transmitted when the period identification data represents a sound-present period. Blank data prepared in advance are selected when the period identification data represents a sound-absent period. Encoded audio signal data of a variable bit rate are received, and the encoded data is selected, decoded, and output at a fixed bit rate when the period identification data represents a sound-present period. Data prepared in advance are outputted when the period identification data represents a sound-absent period.

Abstract: An audio data compression method improves over existing standards because of its encoding strategy for silence. The method analyzes the audio input to an encoder. If the audio is for an analyzed time frame is silence, a single byte output is generated by the encoder. If the next frame is silence, no output is generated. When a receiver receives the compressed data, and detects a one-byte silence signal, it can capture that signal and repeat it to a decoder. When the compressed signal reaches the decoder, it is decompressed into an analog signal.

Abstract: A method for diminishing the effect of transmission errors in samples produced on the output of a decoder in a data transmission system, wherein the samples are attenuated when transmission errors are detected during various successive frames. The invention makes it possible to take isolated transmission errors into account when they are situated in a silence, that is, when they are particularly annoying to the user.

Abstract: An audio stream is analyzed to distinguish silent periods from non-silent periods and an encoded bitstream is generated for the audio stream, wherein the silent periods are represented by one or more sets of canned encoded data corresponding to representative silent periods. In a preferred embodiment, one of the sets of canned encoded data is randomly selected for each silent period. There may be different sets of silent periods corresponding to different types of silent periods, where a particular type of silent period is selected based on some characteristic of the audio stream (e.g., energy level of the silent periods). In addition, the sets of encoded data may be generated from actual silent periods of the audio stream.

Abstract: In a voice coding section 1, a digital voice signal coded in a voice coder 10, a linear predictive coefficient used as a filter coefficient in a short-term predictive filter 102, a pitch period and a pitch predictive coefficient used, respectively, as a tap coefficient and a filter coefficient in a long-term predictive filter 103, and voice/no-voice status information of an input voice, are multiplexed in a multiplexer 12. Only when the voice/no-voice status information indicate the voice state is a cell assembled and transmitted. In a voice decoding section 2, the received cell is disassembled to provide multiplexed coded data. The voice signal is decoded by a short-term synthesis filter and a long term synthesis filter. The short term synthesis filter uses a linear predictive coefficient as a filter coefficient that is decoded from multiplexed coded data.

Abstract: A silence-suppression scheme for a packet voice transmission system (FIG. 1) accurately regenerates the silence signals at the receiving end. The following discipline is implemented at the transmitting end (100): if speech is detected (200), transmit (204) a packet carrying the speech; if silence is detected (200) and the last-transmitted packet carried speech (202), transmit (204) a packet carrying the silence; if silence is detected (200) and the last-transmitted packet carried silence (202), transmit nothing. The following discipline is implemented at the receiving end (101): if a packet is received during a packet time interval (300), output (302) the contents of the packet; if a packet is not received during a packet time interval (300), output (306) again the contents of the last-received packet. Thus, while only one silence-carrying packet is transmitted, the receiver regenerates silence signals for the entire silence interval.

Abstract: A radio paging system with voice transfer function for transmitting a voice message input from an ordinary push-button telephone set to a small-sized receive-only unsophisticated radio pager. A paging station is provided to transmit by radio the message from a telephone network to the radio pager as follows: voice information constituting the message is first converted from analog to digital format, compressed, stored in memory, and scrambled by a privacy function part for transmission. The radio pager in turn demodulates the received information, stores it in memory, retrieves a necessary message therefrom as designated, descrambles the designated message from scrambled state, expands the message from compressed state, and outputs the message as an audible output. In this manner, the user carrying the radio pager is able to get the message from the caller without the risk of being tapped by a third party.

Abstract: An input speech signal is compressed and encoded by a speech encoding unit 3 and sent to an RF transmission processing unit 4 where it is channel-encoded, modulated and transmission-processed so as to be transmitted over an antenna 11. A signal received over the antenna 11 is reception-processed, demodulated and channel-decoded so as to be expanded and decoded a speech decoding unit 6. A recording/playback control unit 8 controls writing of a signal from the speech encoding unit 3 to a semiconductor memory 7 or readout of a signal from the semiconductor memory 7 to the speech encoding unit 3. This enables the semiconductor memory 7 to be efficiently utilized in single/dual communication without increasing the circuit construction.

Abstract: A method and system for adaptively filtering a speech signal. The method includes decomposing the signal into subbands, which may include performing a discrete Fourier transform on the signal to provide approximately orthogonal components. The method also includes determining a speech quality indicator for each subband, which may include estimating a signal-to-noise ratio for each subband. The method also includes selecting a filter for filtering each subband depending on the speech quality indicator, which may include estimating parameters for the filter based on a clean speech signal. The method further includes determining an overall average error for the filtered subbands, which may include calculating a mean-squared error.