Abstract: Acoustic Voice Activity Detection (AVAD) methods and systems are described. The AVAD methods and systems, including corresponding algorithms or programs, use microphones to generate virtual directional microphones which have very similar noise responses and very dissimilar speech responses. The ratio of the energies of the virtual microphones is then calculated over a given window size and the ratio can then be used with a variety of methods to generate a VAD signal. The virtual microphones can be constructed using either an adaptive or a fixed filter.

Abstract: An audio signal quality enhancement apparatus and method. The apparatus includes a pitch calculating unit to extract a pitch period of an audio signal, a frequency domain transforming unit to transform the audio signal to a frequency domain, a frequency band dividing unit to classify the transformed audio signal into audio signals for each of the plurality of frequency bands based on the extracted pitch period, and a pitch enhancement unit to determine a gain based on a volume of the transformed audio signal, and to generate an output signal by multiplying each of the classified audio signals with respect to each of the plurality of frequency bands by the gain, thereby enhancing quality of the audio signal.

Abstract: A conversation detector and detection method is based on voice band energy detection. The detector is formed of a signal preconditioner, a comparator and an analysis unit. The comparator generates signal pulses reduced in resolution and sample rate (e.g., single bit data) and indicative of energy level and/or duration of activity detected in subject audio signals. The analysis unit determines from the generated signal pulses whether a conversation exists in the subject audio signal. The detector is also able to adapt to environmental noise change, automatically calibrate and operate in low power consumption mode.

Abstract: A method for digitally recording an analog audio signal with automatic indexing, having the following steps: (a) an analog audio signal containing audio information and signal pauses is read in, (b) the analog audio signal is converted into digital audio data comprising audio information data and signal pause duration data, (c) the audio information data are stored as information data blocks and the signal pause duration data are stored as signal pause data blocks in a memory, (d) the stored data blocks are read sequentially and an index table is produced, any succession of information data blocks which is not interrupted by a signal pause with a predetermined duration being detected as one cohesive audio information data sequence whose start and end are stored in the index table.

Abstract: Discrimination between at least two classes of events in an input signal is carried out in the following way. A set of frames containing an input signal is received, and at least two different feature vectors are determined for each of said frames. Said at least two different feature vectors are classified using respective sets of preclassifiers trained for said at least two classes of events. Values for at least one weighting factor are determined based on outputs of said preclassifiers for each of said frames. A combined feature vector is calculated for each of said frames by applying said at least one weighting factor to said at least two different feature vectors. Said combined feature vector is classified using a set of classifiers trained for said at least two classes of events.

Abstract: The present invention is directed to a voice activity detector that uses the periodicity of amplitude peaks and valleys to identify signals of substantially fixed power or having periodicity.

Abstract: A speech receiving unit receives a user ID, a speech obtained at a terminal, and an utterance duration, from the terminal. A proximity determining unit calculates a correlation value expressing a correlation between speeches received from plural terminals, compares the correlation value with a first threshold value, and determines that the plural terminals that receive the speeches whose correlation value is calculated are close to each other, when the correlation value is larger than the first threshold value. A dialog detecting unit determines whether a relationship between the utterance durations received from the plural terminals that are determined to be close to each other within an arbitrarily target period during which a dialog is to be detected fits a rule. When the relationship is determined to fit the rule, the dialog detecting unit detects dialog information containing the target period and the user ID.

Abstract: A sound processor including a microphone (1), a pre-amplifier (2), a bank of N parallel filters (3), means for detecting short-duration transitions in the envelope signal of each filter channel, and means for applying gain to the outputs of these filter channels in which the gain is related to a function of the second-order derivative of the slow-varying envelope signal in each filter channel, to assist in perception of low-intensity sort-duration speech features in said signal.

Abstract: A system improves the speech intelligibility and the speech quality of a speech segment. The system includes a dynamic controller that detects a background noise from an input by modeling a signal. A variable gain amplifier adjusts the variable gain of the amplifier in response to an output of dynamic controller. A shaping filter adjusts a speech signal by tilting portions of the speech signal of the dynamic controller.

Abstract: A sound is picked up by a microphone. A speech waveform signal is generated based on the picked up sound. A speech segment or a non-speech segment is detected based on the speech waveform signal. The speech segment corresponds to a voice input period during which a voice is input. The non-speech segment corresponds to a non-voice input period during which no voice is input. A determination signal is generated that indicates whether the picked up sound is the speech segment or the non-speech segment. A detected state of the speech segment is indicated based on the determination signal.

Abstract: A speech enhancement method operative for devices having limited available memory is described. The method is appropriate for very noisy environments and is capable of estimating the relative strengths of speech and noise components during both the presence as well as the absence of speech.

Abstract: A voice activity detection (VAD) device and method provide for a VAD threshold that is adaptive to background noise variation.

Abstract: Microphone arrays (MAs) are described that position and vent microphones so that performance of a noise suppression system coupled to the microphone array is enhanced. The MA includes at least two physical microphones to receive acoustic signals. The physical microphones make use of a common rear vent (actual or virtual) that samples a common pressure source. The MA includes a physical directional microphone configuration and a virtual directional microphone configuration. By making the input to the rear vents of the microphones (actual or virtual) as similar as possible, the real-world filter to be modeled becomes much simpler to model using an adaptive filter.

Abstract: In accordance with an example embodiment of the invention, there is provided an apparatus for detecting voice activity in an audio signal. The apparatus comprises a first voice activity detector for making a first voice activity detection decision based at least in part on the voice activity of a first audio signal received from a first microphone. The apparatus also comprises a second voice activity detector for making a second voice activity detection decision based at least in part on an estimate of a direction of the first audio signal and an estimate of a direction of a second audio signal received from a second microphone. The apparatus further comprises a classifier for making a third voice activity detection decision based at least in part on the first and second voice activity detection decisions.

Abstract: A system and method are disclosed for modifying an audio signal. A pitch associated with the audio signal is detected. A portion of the audio signal that is associated with the detected pitch is modified. Controlling the modification of a primary audio signal is disclosed. The level of a secondary audio signal is monitored. Modification of the primary audio signal is enabled if the level of the secondary audio signal rises above a first prescribed threshold at a time when the primary audio signal is not being modified. Modification of the primary audio signal is disabled if the level of the secondary audio signal drops below a second prescribed threshold at a time when the primary audio signal is being modified.

Abstract: Presented herein are systems and methods for processing sound signals for use with electronic speech systems. Sound signals are temporally parsed into frames, and the speech system includes a speech codebook having entries corresponding to frame sequences. The system identifies speech sounds in an audio signal using the speech codebook.

Abstract: A method for identifying a frame type is disclosed. The present invention includes receiving current frame type information, obtaining previously received previous frame type information, generating frame identification information of a current frame using the current frame type information and the previous frame type information, and identifying the current frame using the frame identification information. And, a method for identifying a frame type is disclosed. The present invention includes receiving a backward type bit corresponding to current frame type information, obtaining a forward type bit corresponding to previous frame type information, generating frame identification information of a current frame by placing the backward type bit at a first position and placing the forward type bit at a second position.

Abstract: Methods and apparatus are disclosed for approximating an MDCT coefficient of a block of windowed sinusoid having a defined frequency, the block being multiplied by a window sequence and having a block length and a block index. A finite trigonometric series is employed to approximate the window sequence. A window summation table is pre-computed using the finite trigonometric series and the defined frequency of the sinusoid. A block phase is computed for each block with the defined frequency, the block length and the block index. An MDCT coefficient is approximated by the dot product of a phase vector computed using the block phase with a corresponding row of the window summation table.

Abstract: The mobile radio terminal includes a speech input unit which inputs a speech signal obtained from speech of a speaking person, an estimating unit which estimates a speech style of the speaking person from the speech signal, and a converting unit which converts the speech signal into a converted speech signal in accordance with the estimated speech style.

Abstract: An apparatus and method for concealing frame erasure and a voice decoding apparatus and method using the same. The frame erasure concealment apparatus includes: a parameter extraction unit determining whether there is an erased frame in a voice packet, and extracting an excitement signal parameter and a line spectrum pair parameter of a previous good frame; and an erasure frame concealment unit, if there is an erased frame, restoring the excitement signal and line spectrum pair parameter of the erased frame by using a regression analysis from the excitement signal and line spectrum pair parameter of the previous good frame. According to the method and apparatus, by predicting and restoring the parameter of the erased frame through the regression analysis, the quality of the restored voice signal can be enhanced and the algorithm can be simplified.

Abstract: In an information detecting apparatus (1), a speech kind discrimination unit (11) discriminates and classifies an audio signal at an information source into kind (category) such as music or speech, etc. on a predetermined time basis, and a memory unit/recording medium (13) records discrimination information thereof. A discrimination frequency calculating unit (15) calculates, on a predetermined time basis, discrimination frequency every kind at a predetermined time period longer than the time unit.

Abstract: A non-intrusive signal quality assessment apparatus includes a feature vector calculator that determines parameters representing frames of a signal and extracts a collection of per-frame feature vectors (?;(n)) representing structural information of the signal from the parameters. A frame selector preferably selects only frames (?\with a feature vector (?;(n)) lying within a predetermined multi-dimensional window (?). Means determine a global feature set (?) over the collection of feature vectors (?;(n)) from statistical moments of selected feature vector components ((1^,02, . . . O11). A quality predictor predicts a signal quality measure (Qj from the global feature set (?)).

Abstract: A voice judging system including feature value extraction means that analyzes a sound signal input from a sound signal input device, and extracts a time series of the feature values, sub-word boundary score calculating means that calculates a time series of sub-word boundary scores, by having reference to sound models of voice stored in a voice model storage unit, temporal regularity analyzing means that analyzes temporal regularity of the sub-word boundary scores, and voice judgment means judges whether the input sound signal is voice or non-voice using of the temporal regularity of the sub-word boundary scores.

Abstract: Encoding audio signals with selecting an encoding mode for encoding the signal categorizing the signal into active segments having voice activity and non-active segments having substantially no voice activity by using categorization parameters depending on the selected encoding mode and encoding at least the active segments using the selected encoding mode.

Abstract: Aspects of a method and system for redundancy-based decoding of voice content in a wireless local area network (WLAN) system are provided. A WLAN receiver may determine whether a decoded portion of a received packet comprises voice content and may select a redundancy-based decoder to decode a remaining portion of the packet when voice content is detected. The redundancy-based decoder may be a Viterbi decoder. The redundancy-based decoder may be selected to decode a determined number of subsequent packets or to decode subsequent packets for a determined amount of time. After decoding the remaining portion of the packet and any subsequent packets, the WLAN receiver may select a standard Viterbi decoder to decode additional received packets. The WLAN receiver may generate at least one signal to select the redundancy-based decoder and the standard Viterbi decoder.

Abstract: A system and method for automatically adjusting floor controls for a conversation is provided. Audio streams are received, which each originate from an audio source. Floor controls for a current configuration including at least a portion of the audio streams are maintained. Conversational characteristics shared by two or more of the audio sources are determined. Possible configurations for the audio streams are identified based on the conversational characteristics. An analysis of the current configuration and the possible configurations is performed. A change threshold is applied to the analysis. When the analysis satisfies the change threshold, the floor controls are automatically adjusted. The audio streams are mixed into one or more outputs based on the adjusted floor controls.

Abstract: A fast accurate multi-channel frequency dependent scheme for analyzing noise in a signal processing system is described herein. Noise is decomposed within each channel into frequency bands and sub-band noise is propagated. To avoid the computational complexity of a convolution, traditional methods either assume the noise to be white, at any point in the signal processing pipeline, or they just ignore spatial operations. By assuming the noise to be white within each frequency band, it is possible to propagate any type of noise (white, colored, Gaussian, non-Gaussian and others) across a spatial transformation in a very fast and accurate manner. To demonstrate the efficacy of this technique, noise propagation is considered across various spatial operations in an image processing pipeline. Furthermore, the computational complexity is a very small fraction of the computational cost of propagating an image through a signal processing system.

Abstract: According to one embodiment of the invention, a method for managing time-sensitive packetized data streams at a receiver includes receiving a time-sensitive packet of a data stream, analyzing an energy level of a payload signal of the packet, and determining whether to drop the packet based on the energy level of the payload signal.

Abstract: A small array microphone system includes an array microphone having a plurality of microphones and operative to provide a plurality of received signals, each microphone providing one received signal. A first voice activity detector (VAD) provides a first voice detection signal generated using the plurality of received signals to indicate the presence or absence of in-beam desired speech. A second VAD provides a second voice detection signal generated using the plurality of received signals to indicate the presence or absence of out-of-beam noise when in-beam desired speech is absent. A reference signal generator provides a reference signal based on the first voice detection signal, the plurality of received signals, and a beamformed signal, wherein the reference signal has the desired speech suppressed. A beamformer provides the beamformed signal based on the second voice detection signal, the reference signal, and the plurality of received signals, wherein the beamformed signal has noise suppressed.

Abstract: In a sound signal processing apparatus, a frame information generation section generates frame information of each frame of a sound signal. A storage stores the frame information generated by the frame information generation section. A first interval determination section determines a first utterance interval in the sound signal. A second interval determination section determines a second utterance interval based on the frame information of the first utterance interval stored in the storage such that the second utterance interval is made shorter than the first utterance interval and confined within the first utterance interval by trimming frames from either of a start point or an end point of the first utterance interval.

Abstract: A method for supporting an encoding of an audio signal is shown, wherein at least a first and a second coder mode are available for encoding a section of the audio signal. The first coder mode enables a coding based on two different coding models. A selection of a coding model is enabled by a selection rule which is based on signal characteristics which have been determined for a certain analysis window. In order to avoid a misclassification of a section after a switch to the first coder mode, it is proposed that the selection rule is activated only when sufficient sections for the analysis window have been received. The invention relates equally to a module in which this method is implemented, to a device and a system comprising such a module and to a software program product including a software code for realizing the proposed method.

Abstract: A system and apparatus for establishing whether a received signal frame is an audio signal frame is disclosed. In one embodiment, the system includes a predetermined position in an audio signal frame containing a piece of secondary information for an audio characteristic of the audio data, with a selection device for selecting a succession of bits which is arranged at the predetermined position in the received signal frame. A decision-making device flags the received signal frame as an audio signal frame if the succession of bits represents the piece of secondary information.

Abstract: There is described a method of encoding an input signal (20) to generate a corresponding encoded output signal (30), and also encoders (10) arranged to implement the method. The method comprises steps of: (a) distributing the input signal to sub-encoders (300, 310, 320) of the encoder (10); (b) processing the distributed input signal (20) at the sub-encoders (300, 310, 320) to generate corresponding representative parameter outputs (200, 210, 220) from the sub-encoders (300, 310, 320); and (c) combining the parameter outputs (200, 210, 220) of the sub-encoders (300, 310, 320) to generate the encoded output signal (30). Processing of the input signal (20) in the sub-encoders (300, 310, 320) involves segmenting the input signal (20) for analysis, such segments having associated temporal durations which are dynamically variable at least partially in response to information content present in the input signal (20).

Abstract: A transient signal encoding method and device, decoding method and device, and processing system, where the transient signal encoding method includes: obtaining a reference sub-frame where a maximal time envelope having a maximal amplitude value is located from time envelopes of all sub-frames of an input transient signal; adjusting an amplitude value of the time envelope of each sub-frame before the reference sub-frame in such a way that a first difference is greater than a preset first threshold, in which the first difference is a difference between the amplitude value of the time envelope of each sub-frame before the reference sub-frame and the amplitude value of the maximal time envelope; and writing the adjusted time envelope into bitstream.

Abstract: A signal processing apparatus includes a decoding unit, an analyzing unit, a synthesizing unit, and a selecting unit. The decoding unit decodes an input encoded audio signal and outputs a playback audio signal. When loss of the encoded audio signal occurs, the analyzing unit analyzes the playback audio signal output before the loss occurs and generates a linear predictive residual signal. The synthesizing unit synthesizes a synthesized audio signal on the basis of the linear predictive residual signal. The selecting unit selects one of the synthesized audio signal and the playback audio signal and outputs the selected audio signal as a continuous output audio signal.

Abstract: A system, method, apparatus, signal-bearing medium, and means for transmitting speech activity in a distributed voice recognition (VR) system. The distributed voice recognition system includes a local VR engine in a subscriber unit (102) and a server VR engine on a server (160). The local VR engine comprises a voice activity detection (VAD) module (106) that detects voice activity within a speech signal, and comprises an advanced feature extraction (AFE) module (104) that extracts features from a speech signal. The detected voice activity information is transmitted over a first wireless communication channel to the server (160). The feature extraction information is transmitted over a second wireless communication channel, separate from the first wireless communication channel, to the server (160). The server (160) processes the received information to determine a linguistic estimate of the electrical speech signal, and transmits the linguistic estimate to the subscriber unit (102).

Abstract: A method of providing voice updates is disclosed and may include receiving a voice update. The method may also include scheduling a voice update window. The voice update window may be a predetermined time window in which a voice update is broadcast.

Abstract: The present invention provides a method, a computer-software-product and an apparatus for enabling a determination of speech related audio data within a record of digital audio data. The method comprises steps for extracting audio features from the record of digital audio data, for classifying one or more subsections of the record of digital audio data, and for marking at least a part of the record of digital audio data classified as speech. The classification of the digital audio data record is performed on the basis of the extracted audio features and with respect to at least one predetermined audio class.

Abstract: An audio decoding system performs frame loss concealment (FLC) when portions of a bit stream representing an audio signal are lost within the context of a digital communication system. The audio decoding system employs two different FLC methods: one designed to perform well for music, and the other designed to perform well for speech. When a frame is deemed lost, the audio decoding system analyzes a previously-decoded audio signal corresponding to previously-decoded frames of an audio bit-stream. Based on the results of the analysis, the lost frame is classified as either speech or music. Using this classification, other signal analysis, and knowledge of the employed FLC methods, the audio decoding system selects the appropriate FLC method which then performs FLC on the lost frame.

Abstract: An automatic system for temporal alignment between a music audio signal and lyrics is provided. The automatic system can prevent accuracy for temporal alignment from being lowered due to the influence of non-vocal sections. Alignment means of the system is provided with a phone model for singing voice that estimates phonemes corresponding to temporal-alignment features or features available for temporal alignment. The alignment means receives temporal-alignment features outputted from temporal-alignment feature extraction means, information on the vocal and non-vocal sections outputted from vocal section estimation means, and a phoneme network, and performs an alignment operation on condition that no phoneme exists at least in non-vocal sections.

Abstract: A VAD/SS system is connected to a channel of a transmission pipe. The channel provides a pathway for the transmission of energy. A method for operating a VAD/SS system includes detecting the energy on the channel, and activating or suppressing activation of the VAD/SS system depending upon the nature of the energy detected on the channel.

Abstract: A method for modifying a window with a frame associated with an audio signal is described. A signal is received. The signal is partitioned into a plurality of frames. A determination is made if a frame within the plurality of frames is associated with a non-speech signal. A modified discrete cosine transform (MDCT) window function is applied to the frame to generate a first zero pad region, where the region has a length of (M?L)/2, where L is an arbitrary value, and a second zero pad region if it was determined that the frame is associated with a non-speech signal. The frame is encoded. The decoder window is the same as the encoder window.

Abstract: There is provided a voice activity detection method for indicating an active voice mode and an inactive voice mode. The method comprises receiving a first portion of an input signal; determining that the first portion of the input signal includes an active voice signal; indicating the active voice mode in response to the determining that the first portion of the input signal includes the active voice signal; receiving a second portion of the input signal immediately following the first portion of the input signal; determining that the second portion of the input signal includes an inactive voice signal; extending the indicating the active voice mode for a period of time after determining that the second portion of the input signal includes the inactive voice signal, wherein the period of time varies based on one or more conditions; and indicating the inactive voice mode after expiration of the period of time.

Abstract: This invention relates to retrieval for multimedia content, and provides a program endpoint time detection apparatus for detecting an endpoint time of a program by performing processing on audio signals of said program, comprising an audio classification unit for classifying said audio signals into a speech signal portion and a non-speech signal portion; a keyword retrieval unit for retrieving, as a candidate endpoint keyword, an endpoint keyword indicating start or end of the program from said speech signal portion; a content analysis unit for performing content analysis on context of the candidate endpoint keyword retrieved by the keyword retrieval unit to determine whether the candidate endpoint keyword is a valid endpoint keyword; and a program endpoint time determination unit for performing statistics analysis based on the retrieval result of said keyword retrieval unit and the determination result of said content analysis unit, and determining the endpoint time of the program.

Abstract: Portions from time-domain speech segments are extracted. Feature vectors that represent the portions in a vector space are created. The feature vectors incorporate phase information of the portions. A distance between the feature vectors in the vector space is determined. In one aspect, the feature vectors are created by constructing a matrix W from the portions and decomposing the matrix W. In one aspect, decomposing the matrix W comprises extracting global boundary-centric features from the portions. In one aspect, the portions include at least one pitch period. In another aspect, the portions include centered pitch periods.

Abstract: A VAD/SS system is connected to a channel of a transmission pipe. The channel provides a pathway for the transmission of energy. A method for operating a VAD/SS system includes detecting the energy on the channel, and activating or suppressing activation of the VAD/SS system depending upon the nature of the energy detected on the channel.

Abstract: An encoding method includes extracting background noise characteristic parameters within a hangover period; for a first superframe after the hangover period, performing background noise encoding based on the extracted background noise characteristic parameters; for superframes after the first superframe, performing background noise characteristic parameter extraction and DTX decision for each frame in the superframes after the first superframe; and for the superframes after the first superframe, performing background noise encoding based on extracted background noise characteristic parameters of the current superframe, background noise characteristic parameters of a plurality of superframes previous to the current superframe, and a final DTX decision. Also, a decoding method and apparatus and an encoding apparatus are disclosed.

Abstract: A hearing aid for improving diminished hearing caused by reduced temporal resolution includes: a speech input unit (201) which receives a speech signal from outside; a speech analysis unit (202) which detects a sound segment and a segment acoustically regarded as soundless from the speech signal received by the speech input unit and detects a consonant segment and a vowel segment within the detected sound segment; and a signal processing unit (204) which temporally increments the consonant segment detected by the speech analysis unit (204) and temporally decrements at least one of the vowel segment and the segment acoustically regarded as soundless detected by the speech analysis unit (204).

Abstract: An intelligent classification method is proposed. The method extracts vocal features from the temporal domain, spectral domain and statistical features for measuring the vocal signal. The measured result is grouped by comparing with the trained data with single voiced source, and then different voices can be separated from the vocal signal to be classified. The vocal features are evaluated from temporal domain and spectral domain and the statistical features, and the method can improve the accuracy of the voice classification.

Abstract: A system and method is provided for obtaining a message type identifier through a speech codec (in-band) such as found in a wireless communication network. A first predetermined sequence with noise-like characteristics is detected and identifies a first message type. A second predetermined sequence with noise-like characteristics is detected and identifies a second message type.