Abstract: Captured vocals may be automatically transformed using advanced digital signal processing techniques that provide captivating applications, and even purpose-built devices, in which mere novice user-musicians may generate, audibly render and share musical performances. In some cases, the automated transformations allow spoken vocals to be segmented, arranged, temporally aligned with a target rhythm, meter or accompanying backing tracks and pitch corrected in accord with a score or note sequence. Speech-to-song music applications are one such example. In some cases, spoken vocals may be transformed in accord with musical genres such as rap using automated segmentation and temporal alignment techniques, often without pitch correction. Such applications, which may employ different signal processing and different automated transformations, may nonetheless be understood as speech-to-rap variations on the theme.

Abstract: A method includes receiving, at a content server from a media device, a request for media content at a first playback rate. The media content is available to the content server at a second playback rate that is different from the first playback rate. The method includes generating modified media content by modifying a first portion of the media content to have a second format corresponding to a third media playback rate. The first portion having a first media characteristic. The third playback rate is different than the first playback rate and is different than the second playback rate. The third playback rate is selected such that the modified media content has a third format corresponding to the first playback rate. The method further includes sending the modified media content from the content server to a media device.

Abstract: Hearing device configuration and hearing treatment using categorical perception; systems and methods for categorical perception based configuration of hearing devices and hearing treatment.

Abstract: An audio packet error concealment system includes an encoding unit for encoding an audio signal consisting of a plurality of frames, and an auxiliary information encoding unit for estimating and encoding auxiliary information about a temporal change of power of the audio signal. The auxiliary information is used in packet loss concealment in decoding of the audio signal. The auxiliary information about the temporal change of power may contain a parameter that functionally approximates a plurality of powers of subframes shorter than one frame, or may contain information about a vector obtained by vector quantization of a plurality of powers of subframes shorter than one frame.

Abstract: The disclosure relates to an audio classifier comprising: a first processor having hard-wired logic configured to receive an audio signal and detect audio activity from the audio signal; and a second processor having reconfigurable logic configured to classify the audio signal as a type of audio signal in response to the first processor detecting audio activity.

Abstract: In accordance with an example embodiment of the present invention, disclosed is a method and an apparatus thereof for selecting a packet loss concealment procedure for a lost audio frame of a received audio signal. A method for selecting a packet loss concealment procedure comprises detecting an audio type of a received audio frame and determining a packet loss concealment procedure based on the audio type. In the method, detecting an audio type comprises determining a stability of a spectral envelope of signals of received audio frames.

Abstract: A processor is disclosed. The processor includes a first-receiver-node for receiving a first-receiver-signal, a second-receiver-node for receiving a second-receiver-signal, a first-output-node for coupling to a digital-baseband-processor, a second-output-node for coupling to the digital-baseband-processor and a first-active-data-pipe extending between the first-receiver-node and the first-output-node. The first-active-data-pipe includes a first-analog-to-digital-converter comprising a first-ADC-input coupled to the first-receiver-node and a first-ADC-output coupled to the first-output-node. The first-analog-to-digital-converter is configured to provide a first-digital-signal to the first-output-node. The processor comprises a first-reference-node and a configurable-data-pipe extending between the second-receiver-node and the second-output-node.

Abstract: An apparatus for processing an input audio signal relies on a cascade of filterbanks, the cascade having a synthesis filterbank for synthesizing an audio intermediate signal from the input audio signal, the input audio signal being represented by a plurality of first subband signals generated by an analysis filterbank, wherein a number of filterbank channels of the synthesis filterbank is smaller than a number of channels of the analysis filterbank. The apparatus furthermore has a further analysis filterbank for generating a plurality of second subband signals from the audio intermediate signal, wherein the further analysis filterbank has a number of channels being different from the number of channels of the synthesis filterbank, so that a sampling rate of a subband signal of the plurality of second subband signals is different from a sampling rate of a first subband signal of the plurality of first subband signals.

Abstract: A method of detecting a particular abnormal sound in an environment with background noise is provided. The method includes acquiring a sound from a microphone, separating abnormal sounds from the input sound based on non-negative matrix factorization (NMF), extracting Mel-frequency cepstral coefficient (MFCC) parameters according to the separated abnormal sounds, calculating hidden Markov model (HMM) likelihoods according to the separated abnormal sounds, and comparing the likelihoods of the separated abnormal sounds with a reference value to determine whether or not an abnormal sound has occurred. According to the method, based on NMF, a sound to be detected is compared with ambient noise in a one-to-one basis and classified so that the sound may be stably detected even in an actual environment with multiple noises.

Abstract: A system, article, and method of random access compression of transducer data for automatic speech recognition decoding.

Abstract: A mobile terminal with a built-in voice message searching function includes: a voice recording module configured to record a voice searching signal from a user and to send the voice searching signal to the pre-processing module for pre-processing, a pre-processing module configured to pre-process the voice searching signal, and to send the pre-processed signal to the matching module for signal matching, a matching module configured to extract a characteristic parameter of the pre-processed signal, to calculate a similarity of the extracted characteristic parameter with a characteristic parameter of a stored voice message, and to send the voice message with a similarity higher than or equal to a threshold to the result outputting module, and a result outputting module configured to display the voice message with the similarity higher than or equal to the threshold on a screen of the mobile terminal.

Abstract: Embodiments of the invention are directed to systems and methods for voice filtering. In some embodiments, an original voice segment from a user may be received. The received original voice segment may be modified using a first predetermined algorithm. The modified voice segment may be sent to an authentication server. At the authentication server, the modified voice segment may be reconstructed into the original voice segment using a second predetermined algorithm. The user may be authenticated for a transaction based at least in part on the reconstructed original voice segment.

Abstract: Multiple audio files may be synchronized using harmonic sound included in audio content obtained from audio tracks. Individual audio tracks are partitioned into multiple temporal windows of a first and second temporal window length. Individual audio waveforms for individual temporal windows of the first and second window length are transformed into frequency space in which energy is represented as a function of frequency. Individual pitches and magnitudes of harmonic sound determined for individual temporal windows may be compared using a multi-resolution framework to correlate pitches and harmonic energy of multiple audio tracks to one another.

Abstract: A method for resampling an audio-frequency signal with an output sampling frequency, for a current signal frame. The method is used when the preceding frame is sampled at a first sampling frequency which is different from a second sampling frequency of the current frame. The method includes: determining a first and second segments of the signal by adding samples at zero at the end of stored samples of the preceding frame and at the start of samples of the current frame, respectively; obtaining the first resampled segment and the second resampled segment by applying at least one resampling filter respectively to the first segment resampling the first frequency at the output frequency, and to the second segment resampling the second frequency at the output frequency; and combining the overlapping portion of the first and second resampled segments to obtain at least one portion of the resampled current frame.

Abstract: A system for exploiting visual information for enhancing audio signals via source separation and beamforming is disclosed. The system may obtain visual content associated with an environment of a user, and may extract, from the visual content, metadata associated with the environment. The system may determine a location of the user based on the extracted metadata. Additionally, the system may load, based on the location, an audio profile corresponding to the location of the user. The system may also load a user profile of the user that includes audio data associated with the user. Furthermore, the system may cancel, based on the audio profile and user profile, noise from the environment of the user. Moreover, the system may include adjusting, based on the audio profile and user profile, an audio signal generated by the user so as to enhance the audio signal during a communications session of the user.

Abstract: This method for synchronizing a first multimedia stream rendered on a first terminal and a second multimedia stream rendered on a second terminal, comprises a step of generation, from an original audio sequence of the first stream, of original audio fingerprints, and further comprises steps of: a) generation from a first sequence of the first stream first audio fingerprints; b) comparison between the first fingerprints and the original fingerprints in order to obtain one or more first synchronization positions; c) correlation of the first sequence with one or more pieces of the original sequence located around the first synchronization positions in order to obtain a second synchronization position; d) rendering of the second stream on the second terminal using the second synchronization position.

Abstract: Methods are disclosed for an encoder to embed a data stream into a quantized PCM digital audio signal and for a corresponding decoder to both retrieve the data stream and losslessly reconstruct the exact original audio. Some methods employ complimentary amplification and attenuation, while others employ gain redistribution. Pre-emphasis and soft clipping techniques are described as methods of losslessly reducing the peak excursion of the PCM audio signal. Also described is the lossless placing of data at predetermined positions within an audio stream.

Abstract: A method includes determining, at an encoder, phase adjustment parameters based on a high-band residual signal. The method also includes inserting the phase adjustment parameters into an encoded version of the audio signal to enable phase adjustment during reconstruction of the audio signal from the encoded version of the audio signal.

Abstract: A method, system, and computer program product for human interface design. Embodiments proceed upon receiving a markup language description of user interface pages (e.g., HTML pages), then, without modifying the user interface page, parsing the markup language description to identify user interface objects configured to perform an operation responsive to a keyboard or mouse or pointing device. One or more mapping techniques serve to relate the parsed-out operation(s) to one or more voice commands. In some embodiments, the parser recognizes interface objects in forms such as a button, a textbox, a checkbox, or an option menu, and the voice commands correspond to an aspect that is displayed when rendering the interface object (e.g., a button label, a menu option, etc.). After receiving a user utterance, the utterance is converted into a text representation which in turn is mapped to voice commands that were parsed from the user interface page.

Abstract: An audio signal processing device comprises a discontinuity detector configured to determine an occurrence of a discontinuity from a sudden increase of an amplitude of decoded audio obtained by decoding the first audio packet which is received correctly after an occurrence of a packet loss, and a discontinuity corrector for correcting the discontinuity of the decoded audio.

Abstract: An apparatus for processing an input audio signal relies on a cascade of filterbanks, the cascade having a synthesis filterbank for synthesizing an audio intermediate signal from the input audio signal, the input audio signal being represented by a plurality of first subband signals generated by an analysis filterbank, wherein a number of filterbank channels of the synthesis filterbank is smaller than a number of channels of the analysis filterbank. The apparatus furthermore has a further analysis filterbank for generating a plurality of second subband signals from the audio intermediate signal, wherein the further analysis filterbank has a number of channels being different from the number of channels of the synthesis filterbank, so that a sampling rate of a subband signal of the plurality of second subband signals is different from a sampling rate of a first subband signal of the plurality of first subband signals.

Abstract: In accordance with an example embodiment of the present invention, disclosed is a method and an apparatus thereof for selecting a packet loss concealment procedure for a lost audio frame of a received audio signal. A method for selecting a packet loss concealment procedure comprises detecting an audio type of a received audio frame and determining a packet loss concealment procedure based on the audio type. In the method, detecting an audio type comprises determining a stability of a spectral envelope of signals of received audio frames.

Abstract: Multiple audio files may be synchronized using harmonic sound included in audio content obtained from audio tracks. Individual audio tracks are partitioned into multiple temporal windows of a first and second temporal window length. Individual audio waveforms for individual temporal windows of the first and second window length are transformed into frequency space in which energy is represented as a function of frequency. Individual pitches and magnitudes of harmonic sound determined for individual temporal windows may be compared using a multi-resolution framework to correlate pitches and harmonic energy of multiple audio tracks to one another.

Abstract: The present invention relates to a frame loss recovering method, an audio decoding method, and an apparatus using the method. A method of recovering a frame loss of an audio signal according to the present invention includes: grouping transform coefficients of at least one frame into a predetermined number of bands among previous frames of a current frame; deriving an attenuation constant according to a tonality of the bands; and recovering transform coefficients of the current frame by applying the attenuation constant to the previous frame of the current frame.

Abstract: A method includes processing media content. The media content includes audio data corresponding to a first audio playback rate and video data corresponding to a first video playback rate. Processing the media content includes identifying a speech portion of the audio data. The speech portion includes a consonant portion. The method further includes producing modified media content. The modified media content is produced based on modifying the video data and modifying the audio data. Modifying the audio data includes applying a non-linear transformation to the speech portion identified in the audio data. The method further includes storing the modified media content.

Abstract: A system and method are provided for improving speech recognition accuracy. Contextual information about user speech may be received, and then speech recognition analysis can be performed on the user speech using the contextual information. This allows the system and method to improve accuracy when performing tasks like searching and navigating using speech recognition.

Abstract: The disclosure provides a method and an apparatus for increasing the capacity of an air interface. The method comprises the following steps that: after a traffic channel is established on a base station side, a base station transmitting a ? rate frame to the air interface in a continuous transmission mode if not capturing a traffic channel frame prefix from a terminal, so as to ensure that the terminal can receive a forward frame of the base station; the base station only reducing the transmission of the ? rate frame after capturing the prefix from the terminal; and the terminal keeping calling and does not release the call if continuous good frames are received during the demodulation of forward traffic frame from the base station. Through the disclosure, the interference between forward channels is reduced, and the capacity of the air interface is increased.

Abstract: A method for recognizing a voice includes receiving, as an input, a voice involving multiple languages, recognizing a first voice of the voice by using a voice recognition algorithm matched to a preset primary language, identifying the preset primary language and a non-primary language different from the preset primary language, which are included in the multiple languages, determining a type of the non-primary language based on context information, recognizing a second voice of the voice in the non-primary language by applying a voice recognition algorithm, which is matched to the non-primary language of the determined type, to the second voice, and outputting a result of recognizing the voice which is based on a result of recognizing the first voice and a result of recognizing the second voice.

Abstract: To achieve sufficient noise cancellation when a reference signal cannot be captured in the proximity of a noise source. The present invention is characterized by comprising: a first input means for obtaining a first mixed signal in which a first signal and a second signal are mixed; a second input means for obtaining a second mixed signal in which the first signal and the second signal are mixed in a different ratio from the first mixed signal; a delay means for generating a delayed first mixed signal by delaying the first mixed signal with a delay amount based on transmission distance from a generation source of the second signal to the second input means; a subtracting means for outputting an estimated first signal in which a pseudo second signal is subtracted from the delayed first mixed signal; and an adaptive filtering means for generating the pseudo second signal applying coefficients which are updated based on the estimated first signal to the second mixed signal.

Abstract: The voiced sound interval classification device comprises a vector calculation unit which calculates, from a power spectrum time series of voice signals, a multidimensional vector series as a vector series of a power spectrum having as many dimensions as the number of microphones, a difference calculation unit which calculates, with respect to each time of the multidimensional vector series, a vector of a difference between the time and the preceding time, a sound source direction estimation unit which estimates, as a sound source direction, a main component of the differential vector, and a voiced sound interval determination unit which determines whether each sound source direction is in a voiced sound interval or a voiceless sound interval by using a predetermined voiced sound index indicative of a likelihood of a voiced sound interval of the voice signal applied at each time.

Abstract: Methods, systems, and computer readable media for enhancing media quality by dynamically inserting a quality enhancement gateway are disclosed. According to one method, steps are performed at a service node. The method includes detecting a condition associated with a session between two endpoints that indicates that the session could benefit from media quality enhancement processing. The method also includes signaling the endpoints to route at least a portion of the session through a quality enhancement gateway (QEG) capable of providing the media quality enhancement processing for the session.

Abstract: A voice recognition system includes a microphone for receiving speech from a user and processing electronics. The processing electronics are in communication with the microphone and are configured to use a plurality of rules to evaluate user interactions with the voice recognition system. The processing electronics automatically determine and set an expertise level in response to and based on the evaluation. The processing electronics are configured to automatically adjust at least one setting of the voice recognition system in response to the set expertise level.

Abstract: An editing device for connecting first and second streams containing variable length coded parameters, includes a decision unit operable to compare an encoded first parameter contained in the first stream with an encoded second parameter contained in the second stream, and decide whether at least one of the first parameter and the second parameter is to be changed, and a replacing unit operable to replace at least one of the first and second parameters with the other code word of the same length as the code words assigned to the first and second parameters, when the decision unit decides that at least one of the parameters is to be changed.

Abstract: Captured vocals may be automatically transformed using advanced digital signal processing techniques that provide captivating applications, and even purpose-built devices, in which mere novice user-musicians may generate, audibly render and share musical performances. In some cases, the automated transformations allow spoken vocals to be segmented, arranged, temporally aligned with a target rhythm, meter or accompanying backing tracks and pitch corrected in accord with a score or note sequence. Speech-to-song music applications are one such example. In some cases, spoken vocals may be transformed in accord with musical genres such as rap using automated segmentation and temporal alignment techniques, often without pitch correction. Such applications, which may employ different signal processing and different automated transformations, may nonetheless be understood as speech-to-rap variations on the theme.

Abstract: Methods and systems for facilitating development of voice-enabled applications are provided. The method may comprise receiving, at a computing device, a plurality of actions associated with a given application, parameters associated with each respective action, and example instructions responsive to respective actions. The method may also comprise determining candidate instructions based on the actions, parameters, and example instructions. Each candidate instruction may comprise one or more grammars recognizable by a voice interface for the given application. The method may further comprise the computing device receiving respective acceptance information for each candidate instruction, and comparing at least a portion of the respective acceptance information with a stored acceptance information log comprising predetermined acceptance information so as to determine a correlation.

Abstract: Compression and decompression of numerical data utilizing single instruction, multiple data (SIMD) instructions is described. The numerical data includes integer and floating-point samples. Compression supports three encoding modes: lossless, fixed-rate, and fixed-quality. SIMD instructions for compression operations may include attenuation, derivative calculations, bit packing to form compressed packets, header generation for the packets, and packed array output operations. SIMD instructions for decompression may include packed array input operations, header recovery, decoder control, bit unpacking, integration, and amplification. Compression and decompression may be implemented in a microprocessor, digital signal processor, field-programmable gate array, application-specific integrated circuit, system-on-chip, or graphics processor, using SIMD instructions. Compression and decompression of numerical data can reduce memory, networking, and storage bottlenecks.

Abstract: A method for identifying an optimal crossing point for concatenation of speech samples within an overlap area is provided. The method includes retrieving a first speech sample and a second speech sample, the second speech sample is concatenated immediately after the first speech sample is concatenated; determining a first region within the ending of the first speech sample and a second region within the beginning of the second speech sample, the first region and the second region are determined respective of relatively high spectral similarity over time between the first speech sample and the second speech sample; identifying an overlap region between the first region and the second region; determining an optimal crossing point between the first speech sample and the second speech sample, the optimal crossing point has a maximum correlation over time; and concatenating the first speech sample and the second speech sample at the optimal crossing point.

Abstract: Embodiments are related to systems and methods for data processing, and more particularly to systems and methods for calibration during data processing. As an example, a data processing system is discussed that includes a sample averaging circuit operable to average digital samples from an analog to digital converter circuit over multiple instances of an analog input to yield an X-average output, and a selector circuit operable to select one of the digital samples or the X-average output as a processing output.

Abstract: One embodiment is a method of presenting an audio-visual work which includes: (a) detecting media work content properties in a visual portion of the audio-visual work using a media work content properties detection apparatus; (b) associating a presentation rate of the portion of the audio-visual work with the detected media work content properties; and (c) presenting the portion of the audio-visual work using the media work content properties detection apparatus; wherein the media work content properties comprise one or more of a predetermined number of items in a video frame, a predetermined number of moving items in a video frame, and one or more predetermined individuals; and wherein the audio-visual work is output from a surveillance camera.

Abstract: There is provided a headset, in particular an aviation headset, having an input for receiving audio signals, an audio storage means for at least temporarily storing audio signals received by way of the input, an output unit for output of the received audio signals to at least one electroacoustic reproduction transducer and an operating unit for releasing audio signals stored in the audio storage means.

Abstract: Methods and apparatus to generate and use content-aware watermarks are disclosed herein. In a disclosed example method, media composition data is received and at least one word present in an audio track of the media composition data is selected. The word is then located in a watermark.

Abstract: An apparatus for decoding data segments representing a time-domain data stream, a data segment being encoded in the time domain or in the frequency domain, a data segment being encoded in the frequency domain having successive blocks of data representing successive and overlapping blocks of time-domain data samples. The apparatus includes a time-domain decoder for decoding a data segment being encoded in the time domain and a processor for processing the data segment being encoded in the frequency domain and output data of the time-domain decoder to obtain overlapping time-domain data blocks. The apparatus further includes an overlap/add-combiner for combining the overlapping time-domain data blocks to obtain a decoded data segment of the time-domain data stream.

Abstract: The present invention is based on the finding that parameters including: a first set of parameters of a representation of a first portion of an original signal and a second set of parameters of a representation of a second portion of the original signal can be efficiently encoded when the parameters are arranged in a first sequence of tuples and a second sequence of tuples. The first sequence of tuples includes tuples of parameters having two parameters from a single portion of the original signal and the second sequence of tuples includes tuples of parameters having one parameter from the first portion and one parameter from the second portion of the original signal. A bit estimator estimates the number of necessary bits to encode the first and the second sequence of tuples. Only the sequence of tuples, which results in the lower number of bits, is encoded.

Abstract: A speech enhancement method is disclosed. The method includes the steps of: receiving a plurality of frames of sound signals by a microphone array; calculating an inter-aural time difference for each frequency band of each frame of the sound signals corresponding to at least one two-microphone set of the microphone array; calculating a plurality of values of cumulative histograms according to the calculated inter-aural time differences, wherein each value of the cumulative histograms is associates with a sound signal intensity of a respective frame; determining a first inter-aural time difference threshold according to the calculated value of the cumulative histograms; and filtering the plurality of frames of sound signals according to the first inter-aural time difference threshold.

Abstract: There is provided a speech processing apparatus including: a data obtaining unit which obtains music progression data defining a property of one or more time points or one or more time periods along progression of music; a determining unit which determines an output time point at which a speech is to be output during reproducing the music by utilizing the music progression data obtained by the data obtaining unit; and an audio output unit which outputs the speech at the output time point determined by the determining unit during reproducing the music.

Abstract: A speech recognition method, medium, and system. The method includes detecting an energy change of each frame making up signals including speech and non-speech signals, and identifying a speech segment corresponding to frames that include only speech signals from among the frames based on the detected energy change.

Abstract: A method for processing multichannel acoustic signals which processes input signals of a plurality of channels including the voices of a plurality of speaking persons. The method is characterized by detecting the voice section of each speaking person or each channel, detecting overlapped sections wherein the detected voice sections are common between channels, determining a channel to be subjected to crosstalk removal and the section thereof by use of at least voice sections not including the detected overlapped sections, and removing crosstalk in the sections of the channel to be subjected to the crosstalk removal.

Abstract: A method and system for performing sample rate conversion is provided. The method may include configuring a system to convert a sample rate of a first audio channel of a plurality of audio channels to produce a first audio stream of samples. The system may be dynamically reconfigured to convert a sample rate of a second of the plurality of audio channels to produce a second audio stream of samples, wherein the first and second audio streams are output from the system at the same time. The method may further include arbitrating between request for additional data from the first and second audio stream of samples, where processing of the first channel is suspended when the request corresponds to a second channel that is of higher priority.

Abstract: Disclosed are systems and methods for managing testing unit latency and measurement uncertainty in computer-based stimulus-response tests. An estimated latency LE and an associated measurement uncertainty are determined as characteristics of a particular testing unit. LE is used as offset for all measurements taken on the testing unit, and results treated subject to the characteristic measurement uncertainty when determining test-taker performance. Estimated actual response times RTE are processed subject to a confidence value determined from the uncertainty. Uncertainty propagation determines test metrics involving a plurality of estimated actual response times RTE, where cumulative uncertainty is reported as a confidence rating in the metric. Overall test results (e.g., pass vs. fail) based on one or more metrics are also reported according to a confidence rating associated with the cumulative uncertainty propagated through the relevant metrics.

Abstract: Various techniques are disclosed for reducing artifacts generated by time compression. by adapting the time compression based on the state of the received audio. The amount of time compression may be bounded based on audio characteristics. Another feature provides a way of determining the most correlated portions of segments of audio. Voiced speech may be distinguished from unvoiced speech. Another feature provides a way of distinguishing between silence, voiced speech, and unvoiced speech. Time compression may be adapted during periods of lengthy silence. Another feature allows for reducing time compression during sensitive portions of the received audio. One or more of these features may be present in different embodiments.