Abstract: Methods, apparatus, systems, and articles of manufacture to perform speed-enhanced playback of recorded media are disclosed. Example apparatus to playback media disclosed herein comprise at least one memory, machine-readable instructions, and processor circuitry to execute the machine-readable instructions to parse an audio frame included in the media to determine a number of skip bytes included in the audio frame, compare the number of skip bytes to a threshold, associate the audio frame with a plurality of candidate frames identified in the media when the number of skip bytes satisfies the threshold, and calculate a speed-enhanced playback rate for the media based on the plurality of candidate frames identified in the media.

Abstract: The present disclosure relates to an audio encoding and decoding (codec) system for voice encoding/decoding using a spectral shaper model. In an embodiment, a method of audio signal decoding comprises: receiving a bit stream associated with an audio signal, the bit stream including encoded transform coefficients, spectral envelope data and one or more parameters of a spectral shaper model, the spectral shaper model indicative of a fundamental frequency of a multi-sinusoidal signal model, where the fundamental frequency corresponds to a time domain delay; decoding the encoded transform coefficients; adjusting the decoded transform coefficients using the spectral envelope data and the spectral shaper model; reconstructing transform coefficients of the audio signal using the adjusted, decoded transform coefficients; and transforming the reconstructed transform coefficients into a time domain audio signal.

Abstract: Provided in the present disclosure are a voice processing method, an apparatus, an electronic device, and a storage medium, the method comprising: detecting the working state of a current call system, and when the working state is a two-end speaking state or a remote-end speaking state, performing compression processing on a subsequent remote-end voice signal, acquiring a near-end voice signal by means of a microphone, performing echo processing on the basis of the near-end voice signal and the compression-processed remote-end voice signal to obtain an echo-processed near-end voice signal and a remaining echo signal, performing non-linear suppression processing on the near-end voice signal and the remaining echo signal, and performing gain control on the suppression-processed near-end voice signal.

Abstract: Methods and apparatuses for detecting user speech are described. In one example, a method for detecting user speech includes receiving a microphone output signal corresponding to sound received at a microphone and identifying a spoken vowel sound in the microphone signal. The method further includes outputting an indication of user speech detection responsive to identifying the spoken vowel sound.

Abstract: According to some aspects, a system for detecting a designated wake-up word is provided, the system comprising a plurality of microphones to detect acoustic information from a physical space having a plurality of acoustic zones, at least one processor configured to receive a first acoustic signal representing the acoustic information received by the plurality of microphones, process the first acoustic signal to identify content of the first acoustic signal originating from each of the plurality of acoustic zones, provide a plurality of second acoustic signals, each of the plurality of second acoustic signals substantially corresponding to the content identified as originating from a respective one of the plurality of acoustic zones, and performing automatic speech recognition on each of the plurality of second acoustic signals to determine whether the designated wake-up word was spoken.

Abstract: Audio data from a first, source speaker is received and processed to determine linguistic units and vocal characteristics corresponding to those linguistic units. The linguistic units may either be determined from received text data or may be determined from the audio data using automatic speech recognition. A model is trained using training data from a second, target speaker. The trained model concatenates the linguistic units with the vocal characteristics to produce output speech that has the “voice” of the target speaker and the vocal characteristics of the source speaker.

Abstract: In one aspect, an example method to be performed by a vehicle-based media system includes (a) receiving audio content; (b) causing one or more speakers to output the received audio content; (c) using a microphone of the vehicle-based media system to capture the output audio content; (d) identifying reference audio content that has at least a threshold extent of similarity with the captured audio content; (e) identifying visual content based at least on the identified reference audio content; and (f) outputting, via a user interface of the vehicle-based media system, the identified visual content.

Abstract: The present invention relates to the field of voice activity detection technologies, and more particularly, to a voice activity detection method. The method comprises: providing an acquisition unit for acquiring an external sound signal; providing a judgment unit for judging whether the sound signal is a voice signal; if the sound signal is a voice signal, starting a voice processing unit for processing the sound signal; if the sound signal is not a voice signal, the voice processing unit is kept in a sleep state. With the voice activity detection method, the voice processing unit with large power consumption is made to be in a sleep state for a long time, and therefore, the entire system can be kept in a low-power consumption state; the voice activity detection method is low in implementation cost and can obtain better performance with a small amount of calculation and less resource consumption.

Abstract: Methods, apparatus, systems and articles of manufacture to perform speed-enhanced playback of recorded media are disclosed. Example media playback devices disclosed herein are to determine a target number of frames of recorded media to drop during playback of the recorded media, the target number determined based on a difference between (1) a total number of frames of the recorded media and (2) a ratio of the total number of frames of the recorded media to a target playback rate. Disclosed example media playback devices are also to select a subset of the frames of the recorded media to drop during the playback of the recorded media, the frames selector to select the subset of the frames based on the target number of frames to drop and skip bytes included in the subset of frames.

Abstract: An apparatus for determining a predetermined characteristic related to a spectral enhancement processing of an audio signal includes a deriver configured for obtaining a spectrum of the audio signal and for deriving a local maximum signal from the spectrum. The apparatus includes a determiner configured for determining a similarity between segments of the local maximum signal and includes a processor for providing an information indicating that the audio signal includes the predetermined characteristic dependent on an evaluation of the similarity.

Abstract: An audio device with an electro-acoustic transducer and a processor that is configured to determine if input audio signals are speech-based, and if the input audio signals are determined to be speech-based apply speech dynamic range compression to the input audio signals, to develop revised audio signals. The revised audio signals are provided to the transducer.

Abstract: Embodiments of the disclosed technologies include finding content of interest in an RF spectrum by automatically scanning the RF spectrum; detecting, in a range of frequencies of the RF spectrum that includes one or more undefined channels, a candidate RF segment; where the candidate RF segment includes a frequency-bound time segment of electromagnetic energy; executing a machine learning-based process to determine, for the candidate RF segment, signal characterization data indicative of one or more of: a frequency range, a modulation type, a timestamp; using the signal characterization data to determine whether audio contained in the candidate RF segment corresponds to a search criterion; in response to determining that the candidate RF segment corresponds to the search criterion, outputting, through an electronic device, data indicative of the candidate RF segment; where the data indicative of the candidate RF segment is output in a real-time time interval after the candidate RF segment is detected.

Abstract: An in-vehicle noise-cancellation system may optimize far-end user experience. The noise-cancellation system may incorporate real-time acoustic input from the vehicle, as well microphones from a telecommunications device. Audio signals from small, embedded microphones mounted in the vehicle can be processed and mixed into an outgoing telecom signal to effectively cancel acoustic energy from one or more unwanted sources in the vehicle. Multiple microphones may be mounted to headrests and spaced apart in one or more directions to give an indication of the direction of incoming sound from one or more listening zones so that sounds from certain zones may be suppressed. Unwanted noise captured by the embedded microphones may be used as direct inputs to the noise-cancellation system. As direct inputs, these streams can, therefore, be cancelled from the outgoing telecom signal, thus providing the user's far-end correspondent with much higher signal-to-noise ratio, call quality, and speech intelligibility.

Abstract: Methods and apparatuses for detecting user speech are described. In one example, a method for detecting user speech includes receiving a microphone output signal corresponding to sound received at a microphone and identifying a spoken vowel sound in the microphone signal. The method further includes outputting an indication of user speech detection responsive to identifying the spoken vowel sound.

Abstract: Background noise estimators and methods are disclosed for estimating background noise in an audio signal. Some methods include obtaining at least one parameter associated with an audio signal segment, such as a frame or part of a frame, based on a first linear prediction gain, calculated as a quotient between a residual signal from a 0th-order linear prediction and a residual signal from a 2nd-order linear prediction for the audio signal segment. A second linear prediction gain is calculated as a quotient between a residual signal from a 2nd-order linear prediction and a residual signal from a 16th-order linear prediction for the audio signal segment. Whether the audio signal segment comprises a pause is determined based at least on the obtained at least one parameter; and a background noise estimate is updated based on the audio signal segment when the audio signal segment comprises a pause.

Abstract: A computer-implemented method of generating advanced feature discrimination vectors (AFDVs) representing sounds forming part of an audio signal input to a device is provided. The method includes taking a plurality of samples of the audio signal, and for each sample of the audio signal taken: performing a signal analysis on the sample to extract one or more high resolution oscillator peaks therefrom; renormalizing the extracted oscillator peaks to eliminate variations in the fundamental frequency and time duration for each sample occurring over the window; normalizing the power of the renormalized extracted oscillator peaks; and forming the renormalized and power normalized extracted oscillator peaks into a respective AFDV for the sample. The method further includes outputting the respective AFDV to a comparison function configured to identify a characteristic of the sample based on a comparison of the respective AFDV with a library of AFDVs associated with known sounds and/or known speakers.

Abstract: In embodiments, a method includes: defining a plurality of visual icons; receiving a voice message, metadata and voice tagging criteria from a first client device; converting the voice message to text; generating a summary of the converted text; generating keywords based on the summary; categorizing the voice message into categories based on the keywords and the metadata; selecting visual icons based on the categories and the tagging criteria; tagging the voice message with the selected visual icons; and sending the tagged voice message to a second client device.

Abstract: A security code input may be obfuscated from a thermal imaging device by randomly heating a random set of inputs of an input device. The security code is inputted on an input device, which communicates with a security system to grant or deny access to a user based on an entry of the security code. The input device includes a plurality of hearing elements. The input device may receive an input from the user. A random set of heating elements including one or more heating elements, are generated from the plurality of heating elements. A temperature is determined for the one or more heating elements of the random set of heating elements. The temperature is then applied to the one or more heating elements of the random set of heating elements of the input device.

Abstract: An audio decoder provides a decoded audio information on the basis of an encoded audio information including linear prediction coefficients (LPC) and includes a tilt adjuster to adjust a tilt of a noise using linear prediction coefficients of a current frame to acquire a tilt information and a noise inserter configured to add the noise to the current frame in dependence on the tilt information. Another audio decoder includes a noise level estimator to estimate a noise level for a current frame using a linear prediction coefficient of at least one previous frame to acquire a noise level information; and a noise inserter to add a noise to the current frame in dependence on the noise level information provided by the noise level estimator. Thus, side information about a background noise in the bit-stream may be omitted. Methods and computer programs serve a similar purpose.

Abstract: A wireless audio system for encoding and decoding an audio signal using spectral bandwidth replication is provided. Bandwidth extension is performed in the time-domain, enabling low-latency audio coding.

Abstract: A speech extraction method based on the supervised learning auditory attention includes: converting an original overlapping speech signal into a two-dimensional time-frequency signal representation by a short-time Fourier transform to obtain a first overlapping speech signal; performing a first sparsification on the first overlapping speech signal, mapping intensity information of a time-frequency unit of the first overlapping speech signal to preset D intensity levels, and performing a second sparsification on the first overlapping speech signal based on information of the preset D intensity levels to obtain a second overlapping speech signal; converting the second overlapping speech signal into a pulse signal by a time coding method; extracting a target pulse from the pulse signal by a trained target pulse extraction network; converting the target pulse into a time-frequency representation of the target speech to obtain the target speech by an inverse short-time Fourier transform.

Abstract: Techniques for reducing the time used to output audio or video include increasing the output rate for portions of the content to reduce the time needed for a user to consume the content. Audio data is analyzed to determine portions that are silent and portions that include speech, such as by determining amplitude and other signal characteristics. Portions that include speech are analyzed to determine an initial rate of speech associated with each portion. Speech characteristics of the portions, such as language, volume, and pitch are used to determine a target maximum comprehensible rate of speech for a user. When audio output is generated, the portions that represent speech are each output at a rate that results in the speech being presented within a threshold of the target rate. The portions that represent silence may be removed, shortened, or output at a faster rate than the portions that represent speech.

Abstract: A response sentence generation apparatus includes a conversion device for converting an input voice of a user into text information, an extraction device for extracting prosodic information from the input voice, a specifying device for specifying an emotion occurrence word indicating an occurrence of an emotion of the user based on the text information and the prosodic information, and a generation device for selecting a character string including the specified emotion occurrence word from the text information and generating a response sentence by performing predetermined processing on the selected character string.

Abstract: Methods, apparatus, systems and articles of manufacture to perform speed-enhanced playback of recorded media are disclosed. Example media playback devices disclosed herein include a target frames calculator to determine a target number of frames of recorded media to drop during playback of the recorded media based on a target playback rate and a total number of frames of the recorded media. Disclosed example media playback devices also include a frames selector to select a subset of the frames of the recorded media to drop during the playback of the recorded media, the frames selector to select the subset of the frames based on the target number of frames to drop and skip bytes included in the subset of frames.

Abstract: A channel information transmission apparatus and method, and a system are disclosed to improve channel information feedback precision. A first device includes: a receiving module, configured to receive a reference signal from a second device; a processing module, configured to obtain a precoding matrix based on the reference signal, and generate first channel information and second channel information that are used to indicate the precoding matrix; and a sending module, configured to send the first channel information and the second channel information to the second device.

Abstract: Techniques are provided for efficient acoustic event detection with reduced resource consumption. A methodology implementing the techniques according to an embodiment includes calculating frames of power spectra based on segments of received acoustic signals. The method further includes two processes, one for detecting impulsive acoustic events and another for detecting continuous acoustic events. The first process includes generating impulsive acoustic event features associated with first and second power spectrum frames, applying a neural network classifier to the impulsive acoustic event features to generate event scores, and detecting an impulsive acoustic event based on those event scores.

Abstract: A headphone system is provided that includes a first earpiece, a first front microphone coupled to the first earpiece to receive a first acoustic signal, a first rear microphone coupled to the first earpiece to receive a second acoustic signal, the second acoustic signal being toward the rear of a user's head relative to the first acoustic signal, and a detection circuit coupled to the first front and rear microphones and configured to compare a front signal derived from the first front microphone to a rear signal derived from the first rear microphone and to selectively indicate that the user is speaking based at least in part upon the comparison.

Abstract: A method and device for automatically increasing the spectral bandwidth of an audio signal including generating a “mapping” (or “prediction”) matrix based on the analysis of a reference wideband signal and a reference narrowband signal, the mapping matrix being a transformation matrix to predict high frequency energy from a low frequency energy envelope, generating an energy envelope analysis of an input narrowband audio signal, generating a resynthesized noise signal by processing a random noise signal with the mapping matrix and the envelope analysis, high-pass filtering the resynthesized noise signal, and summing the high-pass filtered resynthesized noise signal with the original an input narrowband audio signal. Other embodiments are disclosed.

Abstract: A head-mounted wearable device incorporates a transducer that operates as a bone conduction (BC) microphone. Vibrations from a user's speech are transferred through the head of the user to the BC microphone. An air conduction (AC) microphone detects sound transferred via air. Signals from the BC microphone and the AC microphone are compared to determine if a common signal is present in both. For example, both signals may have a cross-correlation that exceeds a threshold value. Based on the comparison, voice activity data is generated that indicates the user wearing the device is speaking.

Abstract: An audio processing apparatus is provided that includes an acquirer that acquires a surrounding audio signal indicating a sound surrounding a user. The audio processing apparatus also includes an audio extractor that extracts, from the acquired surrounding audio signal, a providing audio signal indicating a sound to be provided to the user. The audio processing apparatus further includes an output that outputs a first audio signal, indicating a main sound, and the providing audio signal.

Abstract: In accordance with embodiments of the present disclosure, an integrated circuit for implementing at least a portion of an audio device may include an audio output configured to reproduce audio information by generating an audio output signal for communication to at least one transducer of the audio device, a microphone input configured to receive an input signal indicative of ambient sound external to the audio device, and a processor configured to implement an impulsive noise detector. The impulsive noise detector may comprise a plurality of processing blocks for determining a feature vector based on characteristics of the input signal and a neural network for determining based on the feature vector whether the impulsive event comprises a speech event or a noise event.

Abstract: A signal processor comprising: a modelling block, configured to receive a frequency-domain-input-signal, a fundamental-frequency-signal representative of a fundamental frequency of the frequency-domain-input-signal; and configured to provide a pitch-model-signal based on a periodic function, the pitch-model-signal spanning a plurality of discrete frequency bins, each discrete frequency bin having a respective discrete frequency bin index, wherein within each discrete frequency bin the pitch-model-signal is defined by: the periodic function; the fundamental frequency; the frequency-domain-input-signal; and the respective discrete frequency bin index. The signal processor further comprises a manipulation block, configured to provide an output-signal based on the frequency-domain-input-signal and the pitch-model-signal.

Abstract: A method and an apparatus for synthesizing an audio signal are described. A spectral tilt is applied to the code of a codebook used for synthesizing a current frame of the audio signal. The spectral tilt is based on the spectral tilt of the current frame of the audio signal. Further, an audio decoder operating in accordance with the inventive approach is described.

Abstract: A speech enhancement method is provided. The speech enhancement method includes: estimating a direction of a speaker by using an input signal, generating direction information indicating the estimated direction, detecting speech of a speaker based on a result of the estimating the direction, and enhancing the speech of the speaker by using the direction information based on a result of the detecting the speech.

Abstract: A method for processing an initial signal includes a useful signal and added noise, which comprises a step of frequency selective analysis providing starting from initial signal a plurality of wideband analysis signals corresponding to one of the analyzed frequencies, and comprising the following actions: zero or more complex frequency translations, one or more undersampling operations, computation of the instantaneous Amplitude, of the instantaneous Phase, and of the instantaneous Frequency of the wideband analysis signals. This information then allow to detect modulations of signals included in high levels of noise and to detect with a good probability the presence of a signal in a high level of noise.

Abstract: A sound recognition system including time-dependent analog filtered feature extraction and sequencing. An analog front end (AFE) in the system receives input analog signals, such as signals representing an audio input to a microphone. Features in the input signal are extracted, by measuring such attributes as zero crossing events and total energy in filtered versions of the signal with different frequency characteristics at different times during the audio event. In one embodiment, a tunable analog filter is controlled to change its frequency characteristics at different times during the event. In another embodiment, multiple analog filters with different filter characteristics filter the input signal in parallel, and signal features are extracted from each filtered signal; a multiplexer selects the desired features at different times during the event.

Abstract: An audio encoder for encoding an audio signal has: a first encoding processor for encoding a first audio signal portion in a frequency domain, having: a time frequency converter for converting the first audio signal portion into a frequency domain representation; an analyzer for analyzing the frequency domain representation to determine first spectral portions to be encoded with a first spectral resolution and second regions to be encoded with a second resolution; and a spectral encoder for encoding the first spectral portions with the first spectral resolution and encoding the second portions with the second resolution; a second encoding processor for encoding a second different audio signal portion in the time domain; a controller for analyzing and determining, which portion of the audio signal is the first audio signal portion encoded in the frequency domain and which portion is the second audio signal portion encoded in the time domain; and an encoded signal former for forming an encoded audio signal havi

Abstract: A transient detector (100) analyzes (110) a given frame n of the input audio signal to determine, based on audio signal characteristics of the given frame n, a transient hangover indicator for a following frame n+1, and signals (120) the determined transient hangover indicator to an associated audio encoder (10) to enable proper encoding of the following frame n+1.

Abstract: An audio decoder provides a decoded audio information on the basis of an encoded audio information including linear prediction coefficients (LPC) and includes a tilt adjuster to adjust a tilt of a noise using linear prediction coefficients of a current frame to acquire a tilt information and a noise inserter configured to add the noise to the current frame in dependence on the tilt information. Another audio decoder includes a noise level estimator to estimate a noise level for a current frame using a linear prediction coefficient of at least one previous frame to acquire a noise level information; and a noise inserter to add a noise to the current frame in dependence on the noise level information provided by the noise level estimator. Thus, side information about a background noise in the bit-stream may be omitted. Methods and computer programs serve a similar purpose.

Abstract: A process at an electronic computing device (device) for automatic and selective context-based gating of an electronic digital assistant speech-output function includes detecting, via a sensor communicatively coupled to the device or via a notification received at the device, an event associated with a need to reduce a cognitive load on the user. Responsively, temporarily gating a portion of an electronic digital assistant speech-output function to prevent reproduction to the user of one or more first speech-output events generated during a first period of time associated with the event. Subsequently, and after detecting that the event has ended, ending the temporary gating to allow reproduction of one or more second speech-output events generated during a second period of time after the event has ended.

Abstract: An approach is provided that assists visually impaired users. The approach analyzes a document that is being utilized by the visually impaired user. The analysis derives a sensitivity of the document. A vocal characteristic corresponding to the derived sensitivity is retrieved. Text from the document is audibly read to the visually impaired user with a text to speech process that utilizes the retrieved vocal characteristic. The retrieved vocal characteristic conveys the derived sensitivity of the document to the visually impaired user.

Abstract: In accordance with embodiments of the present disclosure, an integrated circuit for implementing at least a portion of an audio device may include an audio output configured to reproduce audio information by generating an audio output signal for communication to at least one transducer of the audio device, a microphone input configured to receive an input signal indicative of ambient sound external to the audio device and a processor configured to implement an impulsive noise detector. The impulsive noise detector may include a sudden onset detector for predicting an occurrence of a signal burst event of the input signal and an impulsive detector for determining whether the signal burst event comprises a speech event or a noise event.

Abstract: An encoding apparatus is an encoding apparatus for encoding a time-series signal for each of predetermined time sections in a frequency domain, wherein a parameter ? is a positive number, the parameter ? corresponding to a time-series signal is a shape parameter of generalized Gaussian distribution that approximates a histogram of a whitened spectral sequence, which is a sequence obtained by dividing a frequency domain sample sequence corresponding to the time-series signal by a spectral envelope estimated by regarding the ?-th power of absolute values of the frequency domain sample sequence as a power spectrum, and any of a plurality of parameters ? is selective or the parameter ? is variable for each of the predetermined time sections; and the encoding apparatus comprises an encoding portion encoding the time-series signal for each of the predetermined time sections by an encoding process with a configuration identified at least based on the parameter ? for each of the predetermined time sections.

Abstract: A voice starting end detection apparatus includes a first detector that detects a starting end of a voice segment from input signals that are input in a time series, a first transmitting unit that transmits, when the starting end is detected, input signals subsequent to the starting end, and a first receiving unit that receives a terminal end detection signal indicating that a terminal end of the voice segment has been detected. The voice terminal end detection apparatus includes a second receiving unit that receives input signals subsequent to the starting end, a second detector that detects the terminal end from the received input signals, a second transmitting unit that transmits, when the terminal end is detected, the terminal end detection signal. The first transmitting unit stops transmitting the input signals when the first receiving unit receives the terminal end detection signal.

Abstract: Apparatus, methods, and systems that operate to perform machine-control of a device based on machine-detected transitions are disclosed.

Abstract: Embodiments of the present disclosure provide a decoding method and a decoding apparatus. The decoding method includes: in a case in which it is determined that a current frame is a lost frame, synthesizing a high frequency band signal; determining subframe gains of multiple subframes of the current frame; determining a global gain of the current frame; and adjusting, according to the global gain and the subframe gains of the multiple subframes, the synthesized high frequency band signal to obtain a high frequency band signal of the current frame. A subframe gain of the current frame is obtained according to a gradient between subframe gains of subframes previous to the current frame, so that transition before and after frame loss is more continuous, thereby reducing noise during signal reconstruction, and improving speech quality.

Abstract: A home audio system that includes an audio receiver and one or more loudspeaker arrays is described. The audio receiver measures the acoustic properties of the room in which the loudspeaker arrays reside and the audio characteristics of the sound program content to be played through the loudspeaker arrays. Based on these measurements, the audio receiver assigns a directivity ratio and potentially various beam patterns to one or more segments of the sound program content. The assigned directivity ratio is used by the receiver to play the segment of the sound program content through the loudspeaker arrays. Other embodiments are also described.

Abstract: The present disclosure provides for devices, systems, and methods which optimize throughput of bonded connections over multiple variable bandwidth logical paths by adjusting a tunnel bandwidth weighting schema during a data transfer session in response to a change in bandwidth capabilities of one or more tunnels. By making such adjustments, embodiments of the present invention are able to optimize the bandwidth potential of multiple connections being used in a session, while minimizing the adverse consequences of reduced bandwidth issues which may occur during the data transfer session.

Abstract: An apparatus for generating a bandwidth extended signal includes an anti-sparseness processing unit to perform anti-sparseness processing on a low-frequency spectrum; and a frequency domain high-frequency extension decoding unit to perform high-frequency extension encoding in the frequency domain on the low-frequency spectrum on which the anti-sparseness processing is performed.

Abstract: Disclosed are a voice activity detection method and device, wherein the method includes: obtaining a combined VAD judgment result according to the number of continuous active frames, an average total SNR of all sub-bands, a tonal signal flag, and at least two existing VAD judgment results (107). The method and device are suitable for voice service, solve the problem of inaccurate VAD detection and realize highly accurate VAD judgment.