Abstract: A real-time processor-implemented translation method and apparatus is provided. The real-time translation method includes receiving a content, determining a delay time for real-time translation based on a silence interval of the received content and an utterance interval of the received content, generating a translation result by translating a language used in the received content, and synthesizing the translation result and the received content.

Abstract: A method for muting and unmuting a microphone is provided. The method includes providing a processor, receiving an input microphone signal, measuring the input microphone signal for a loudness level at a sampling rate, calculating a mute threshold level, checking if the loudness level is higher than or equal to the mute threshold level, and resetting a mute delay timer upon determining that the loudness level is higher than or equal to the mute threshold level and obtaining the input microphone signal, or checking if the mute delay timer is running upon determining that the loudness level is not higher than or equal to the mute threshold level and attenuating the input microphone signal if the mute delay timer is not running or obtaining the input microphone signal if the mute delay timer is still running, and writing the input microphone signal or attenuated input microphone signal to an output buffer.

Abstract: A Unified Speech and Audio Codec (USAC) that may process a window sequence based on mode switching is provided. The USAC may perform encoding or decoding by overlapping between frames based on a folding point when mode switching occurs. The USAC may process different window sequences for each situation to perform encoding or decoding, and thereby may improve a coding efficiency.

Abstract: Systems and methods are disclosed herein for remote application sharing. An exemplary method comprises detecting a user establishing a connection with a remote application server, authenticating the user based on login information associated with the user, determining that the user has requested execution of a shared application hosted on the remote application server, responsive to determining that the user has requested execution of the shared application, gathering information for accessing the shared application hosted on the remote application server, establishing a user session for executing the shared application, generating an application link comprising the information for accessing the shared application over the user session and publishing the application link for distribution to one or more third party users, wherein activation of the application link by the one or more third party users shares the user session with the one or more third party users.

Abstract: A cross-lingual voice conversion system and method comprises a voice feature extractor configured to receive a first voice audio segment in a first language and a second voice audio segment in a second language, and extract, respectively, audio features comprising first-voice, speaker-dependent acoustic features and second-voice, speaker-independent linguistic features. One or more generators are configured to receive extracted features, and produce therefrom a third voice candidate keeping the first-voice, speaker-dependent acoustic features and the second-voice, speaker-independent linguistic features, wherein the third voice candidate speaks the second language. One or more discriminators are configured to compare the third voice candidate with the ground truth data, and provide results of the comparison back to the generator for refining the third voice candidate.

Abstract: Provided is pitch enhancement processing having little unnaturalness even in time segments for consonants, and having little unnaturalness to listeners caused by discontinuities even when time segments for consonants and other time segments switch frequently. A pitch emphasis apparatus carries out the following as the pitch enhancement processing: for a time segment in which a spectral envelope of a signal has been determined to be flat, obtaining an output signal for each of times in the time segment, the output signal being a signal including a signal obtained by adding (1) a signal obtained by multiplying the signal of a time, further in the past than the time by a number of samples T0 corresponding to a pitch period of the time segment, a pitch gain ?0 of the time segment, a predetermined constant B0, and a value greater than 0 and less than 1, to (2) the signal of the time.

Abstract: A method for processing an audio signal includes: receiving a bitstream corresponding to the audio signal; obtaining a silence insertion descriptor (SID) type of a current frame of the audio signal by decoding the bitstream; obtaining a low-band parameter of the current frame by decoding the bitstream; obtaining a low-band signal of the current frame based on the low-band parameter; obtaining, based on the SID type of the current frame, a high-band parameter of the current frame; obtaining a high-band signal of the current frame based on the high-band parameter; and obtaining a synthesis signal of the current frame based on the low-band signal and the high-band signal.

Abstract: Quantizing speech model parameters includes, for each of multiple vectors of quantized excitation strength parameters, determining first and second errors between first and second elements of a vector of excitation strength parameters and, respectively, first and second elements of the vector of quantized excitation strength parameters, and determining a first energy and a second energy associated with, respectively, the first and second errors. First and second weights for, respectively, the first error and the second error, are determined and are used to produce first and second weighted errors, which are combined to produce a total error. The total errors of each of the multiple vectors of quantized excitation strength parameters are compared and the vector of quantized excitation strength parameters that produces the smallest total error is selected to represent the vector of excitation strength parameters.

Abstract: A decoding apparatus includes: a bandwidth extending part 25 obtaining a decoded extended frequency spectrum sequence by arranging samples based on K samples included in a frequency-domain sample sequence obtained by decoding, on a higher side than the frequency-domain sample sequence; and a fricative sound adjustment releasing part 23 obtaining, if inputted information indicating whether a hissing sound or not indicates being a hissing sound, what is obtained by exchanging all or a part of a low-side frequency sample sequence existing on a lower side than a predetermined frequency in the decoded extended frequency spectrum sequence for all or a part of a high-side frequency sample sequence existing on a higher side than the predetermined frequency in the decoded extended frequency spectrum sequence as an adjusted frequency spectrum sequence, the number of all or the part of the high-side frequency spectrum sequence being the same as the number of all or the part of the low-side frequency spectrum sequence.

Abstract: Embodiments of the invention may be used to implement a rate converter that includes: 6 channels in forward (audio) path, each channel having a 24-bit signal path per channel, an End-to-end SNR of 110 dB, all within the 20 Hz to 20 KHz bandwidth. Embodiment may also be used to implement a rate converter having: 2 channels in a reverse path, such as for voice signals, 16-bit signal path per channel, an End-to-end SNR of 93 dB, all within 20 Hz to 20 KHz bandwidth. The rate converter may include sample rates such as 8, 11.025, 12, 16, 22.05, 24, 32 44.1, 48, and 96 KHz. Further, rate converters according to embodiments may include a gated clock in low-power mode to conserve power.

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: The present invention relates to coding of audio signals, and in particular to high frequency reconstruction methods including a frequency domain harmonic transposer. A system and method for generating a high frequency component of a signal from a low frequency component of the signal is described.

Abstract: A voice event detection apparatus is disclosed. The apparatus comprises a vibration to digital converter and a computing unit. The vibration to digital converter is configured to convert an input audio signal into vibration data. The computing unit is configured to trigger a downstream module according to a sum of vibration counts of the vibration data for a number X of frames. In an embodiment, the voice event detection apparatus is capable of correctly distinguishing a wake phoneme from the input vibration data so as to trigger a downstream module of a computing system. Thus, the power consumption of the computing system is saved.

Abstract: Provided is pitch enhancement processing having little unnaturalness even in time segments for consonants, and having little unnaturalness to listeners caused by discontinuities even when time segments for consonants and other time segments switch frequently. A pitch emphasis apparatus carries out the following as the pitch enhancement processing: for a time segment in which a spectral envelope of a signal has been determined to be flat, obtaining an output signal for each of times in the time segment, the output signal being a signal including a signal obtained by adding (1) a signal obtained by multiplying the signal of a time, further in the past than the time by a number of samples T0 corresponding to a pitch period of the time segment, a pitch gain ?0 of the time segment, a predetermined constant B0, and a value greater than 0 and less than 1, to (2) the signal of the time.

Abstract: A method, computer program, and computer system is provided for converting a singing voice of a first person associated with a first speaker to a singing voice of a second person using a speaking voice of the second person associated with a second speaker. A context associated with one or more phonemes corresponding to the singing voice of a first person is encoded, and the one or more phonemes are aligned to one or more target acoustic frames based on the encoded context. One or more mel-spectrogram features are recursively generated from the aligned phonemes, the target acoustic frames, and a sample of the speaking voice of the second person. A sample corresponding to the singing voice of a first person is converted to a sample corresponding to the second singing voice using the generated mel-spectrogram features.

Abstract: A method of determining noise reduction in a signal includes transforming the signal to generate a spectrogram; determining sharp change in a frequency spectrum for each frame in the spectrogram; and comparing a counted number of frames having sharp change with a predetermined value. The signal is determined to be subject to noise reduction if the counted number is greater than the predetermined value.

Abstract: Various embodiments of the present technology may provide methods and apparatus for a voice detector. The voice detector may provide a microphone and an audio processor. The microphone may provide an active signal generator configured to generate an active signal. The active signal may indicate when the signal level of detected audio is above or below a threshold level with a first state and a second state. The active signal may prevent activity at the microphone I/O interface and may prevent activity at the audio processor's internal logic.

Abstract: A device implementing a system for mitigating noise includes at least one processor configured to receive a first audio signal corresponding to a first microphone, and determine whether wind noise is present based at least in part on the first audio signal. The processor is configured to select, based on the determining, a second audio signal from between second and third microphones. The second microphone is disposed at a location that experiences less echo coupling when the device is in a particular orientation with respect to a user. The third microphone is disposed at another location that experiences less wind noise. The processor is configured to determine voice and noise reference values based on the first and the selected second audio signals, and perform noise suppression with respect to at least one of the first or the selected second audio signal, based on the voice or the noise reference value.

Abstract: A speech processing method and a terminal are provided. The method includes: receiving signals from a plurality of microphones; performing, by using a same sampling rate, analog-to-digital conversion on the plurality of paths of signals received from the plurality of microphones, to obtain a plurality of paths of time-domain digital signals; performing time-to-frequency-domain conversion on the plurality of paths of time-domain digital signals to obtain a plurality of paths of frequency-domain signals; and determining a signal type of the primary frequency-domain signal based on at least one of a sound pressure difference between the primary frequency-domain signal and each of N paths of secondary frequency-domain signals in the M paths of secondary frequency-domain signals, a phase difference between the primary frequency-domain signal and each of the N paths of secondary frequency-domain signals, and a frequency distribution characteristic of the primary frequency-domain signal.

Abstract: A device includes a receiver configured to receive an audio frame of an audio stream. The audio frame includes information that indicates a coded bandwidth of the audio frame. The device also includes a decoder configured to generate first decoded speech associated with the audio frame and to determine an output mode of the decoder based at least in part on the information that indicates the coded bandwidth. A bandwidth mode indicated by the output mode of the decoder is different than a bandwidth mode indicated by the information that indicates the coded bandwidth. The decoder is further configured to output second decoded speech based on the first decoded speech. The second decoded speech is generated according to an output mode of the decoder.

Abstract: A method for processing speech includes: executing a acquiring process that includes acquiring a speech signal; executing a detection process that includes detecting a first frequency spectrum from the speech signal; executing a calculation process that includes calculating a second spectrum based on an envelope of the first spectrum; executing a correction process that includes correcting the first spectrum based on comparison between a first amplitude of the first spectrum and a second amplitude of the second spectrum; executing a estimation process that includes estimating a pitch frequency of the speech signal in accordance with correlation between the corrected first frequency spectrum and periodic signals corresponding to frequencies in a certain band.

Abstract: A computer-implemented method for processing a speech signal, includes: identifying speech segments in an input speech signal; calculating an upper variance and a lower variance, the upper variance being a variance of upper spectra larger than a criteria among speech spectra corresponding to frames in the speech segments, the lower variance being a variance of lower spectra smaller than a criteria among the speech spectra corresponding to the frames in the speech segments; determining whether the input speech signal is a special input speech signal using a difference between the upper variance and the lower variance; and performing speech recognition of the input speech signal which has been determined to be the special input speech signal, using a special acoustic model for the special input speech signal.

Abstract: A virtual physical layer may be provided. When providing the virtual physical layer, a remote radio head may be used. The remote radio head may comprise a first interface device, a second interface device, a digital-to-analog converter, and an analog-to-digital converter. The first interface device may be connected to a virtual physical layer instance instantiated in a cloud-based environment. The second interface device may be connected to customer premises equipment. The digital-to-analog converter may be connected between the first interface device and the second interface device and the analog-to-digital converter may also be connected between the first interface device and the second interface device.

Abstract: A method and a system for decomposition of acoustic signal into sound objects having the form of signals with slowly-varying amplitude and frequency, as well as sound objects and their use. The object is achieved by a method for decomposing an acoustic signal into digital sound objects, a digital sound object representing a component of the acoustic signal, the component having a waveform, comprising the steps of converting the analogue acoustic signal into a digital input signal (PIN); determining an instantaneous frequency component of the digital input signal, using a digital filter bank; determining an instantaneous amplitude of the instantaneous frequency component; determining an instantaneous phase of the digital input signal associated with the instantaneous frequency; creating at least one digital sound object, based on the determined instantaneous frequency, phase and amplitude; and storing the digital sound object in a sound object database.

Abstract: Methods, an encoder and a decoder are configured for transition between frames with different internal sampling rates. Linear predictive (LP) filter parameters are converted from a sampling rate S1 to a sampling rate S2. A power spectrum of a LP synthesis filter is computed, at the sampling rate S1, using the LP filter parameters. The power spectrum of the LP synthesis filter is modified to convert it from the sampling rate S1 to the sampling rate S2. The modified power spectrum of the LP synthesis filter is inverse transformed to determine autocorrelations of the LP synthesis filter at the sampling rate S2. The autocorrelations are used to compute the LP filter parameters at the sampling rate S2.

Abstract: Methods, an encoder and a decoder are configured for transition between frames with different internal sampling rates. Linear predictive (LP) filter parameters are converted from a sampling rate S1 to a sampling rate S2. A power spectrum of a LP synthesis filter is computed, at the sampling rate S1, using the LP filter parameters. The power spectrum of the LP synthesis filter is modified to convert it from the sampling rate S1 to the sampling rate S2. The modified power spectrum of the LP synthesis filter is inverse transformed to determine autocorrelations of the LP synthesis filter at the sampling rate S2. The autocorrelations are used to compute the LP filter parameters at the sampling rate S2.

Abstract: A voice coder configured to resolve periodic and aperiodic components of spectra is disclosed. The method of voice coding includes parsing the speech signal into a plurality of speech frames; for each of the plurality of speech frames: (a) generating the spectra for the speech frame, (b) parsing the spectra of the speech frame into a plurality of sub-bands, (c) transforming each of the plurality of sub-bands into a time-domain envelope signal, and (d) generating a plurality of sub-band voicing factors, wherein each sub-band voicing factor indicates the harmonicity of one of the plurality of sub-bands, and each sub-band voicing factor is based on the periodicity of one of said time-domain envelope signals associated with one of the plurality of sub-bands.

Abstract: Example systems and methods capture a first plurality of portions of audio data by periodically capturing the audio data at first intervals. Embodiments detect speech onset in the audio data. Responsive to detection of the speech onset, systems and methods switch from periodically capturing the audio data to continuously capturing the audio data. Embodiments combine at least one captured portion of the first plurality of captured portions of the audio data with the continuously captured audio data to provide contiguous audio data.

Abstract: An electronic device or method for adjusting a gain on a voice operated control system can include one or more processors and a memory having computer instructions. The instructions, when executed by the one or more processors causes the one or more processors to perform the operations of receiving a first microphone signal, receiving a second microphone signal, updating a slow time weighted ratio of the filtered first and second signals, and updating a fast time weighted ratio of the filtered first and second signals. The one or more processors can further perform the operations of calculating an absolute difference between the fast time weighted ratio and the slow time weighted ratio, comparing the absolute difference with a threshold, and increasing the gain when the absolute difference is greater than the threshold. Other embodiments are disclosed.

Abstract: Apparatuses, systems, methods, and media for filtering a data stream are provided. The data stream is partitioned into a plurality of data stream segments. An acoustic parameter is measured in each of the data stream segments. It is determined whether the acoustic parameter satisfies a first predetermined condition. The first predetermined condition includes a number of variances, in which the acoustic parameter exceeds a predetermined variance threshold, exceeding a predetermined number threshold. An extraneous portion of the data stream is identified in which the first predetermined condition is satisfied. It is determined whether the extraneous portion satisfies a second predetermined condition in the data stream. The extraneous portion is deleted from the data stream to produce a filtered data stream in response to the second predetermined condition being satisfied.

Abstract: Systems and methods for structuring information include determining information quantity (IQ) and information value (IV) in an original digital information file (ODIF). An initial manipulation process applied to the ODIF forms a first resulting DIF (FRDIF), and a subsequent manipulation process applied to the FRDIF forms a second resulting DIF, wherein each manipulation process removes at least one element of the processed DIF and/or represents an element combination with a representative element and a first indicia of an interrelationship between the representative element and one or more elements in the combination, to reduce the IQ of the processed DIF, while retaining the IV thereof within a threshold. Manipulation processes are successively applied to the previously resulting DIF until successive applications do not achieve a threshold reduction in IQ. The last resulting DIF has a primary structure with a reduced IQ and an IV within the threshold of the original IV.

Abstract: A comfort noise generation apparatus constituted of: near and far end speech detectors arranged to detect speech activity in near-end and far-end signals and a comfort noise generator, wherein responsive to an indication from the near-end speech detector that speech activity is absent on the near-end signal and an indication from the far-end silence detector that speech activity is absent on the far-end signal, the comfort noise generator is arranged to initiate a determination of an estimation of near-end background noise, wherein responsive to an indication from the near-end speech detector that speech activity is present on the near-end signal or an indication from the far-end silence detector that speech activity is present on the far-end signal, the comfort noise generator is arranged to terminate the estimation determination of near-end background noise, and wherein the comfort noise generator is arranged to output a function of the near-end background noise estimation.

Abstract: An oversampling LPF unit receives a sound signal. A differentiator differentiates the sound signal. An overtone computation unit generates an overtone signal by multiplying a signal differentiated by the differentiator by the sound signal from the oversampling LPF unit. A HPF unit filters the overtone signal generated by the overtone computation unit. A combiner combines the overtone signal filtered by the HPF unit and the sound signal from the oversampling LPF unit.

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 device for signal processing includes a receiver and a high-band excitation signal generator. The receiver is configured to receive a parameter associated with a bandwidth-extended audio stream. The high-band excitation signal generator is configured to determine a value of the parameter. The high-band excitation signal generator is also configured to select, based on the value of the parameter, one of target gain information associated with the bandwidth-extended audio stream or filter information associated with the bandwidth-extended audio stream. The high-band excitation signal generator is further configured to generate a high-band excitation signal based on the one of the target gain information or the filter information.

Abstract: Method and apparatus for segmenting speech by detecting the pauses between the words and/or phrases, and to determine whether a particular time interval contains speech or non-speech, such as a pause.

Abstract: An encoding technique encoding a sound signal at a low bit rate with reduced processing. The technique includes: an interval determination determining an interval T between samples corresponding to periodicity of an audio signal or an integer multiple of a fundamental frequency of the audio signal from a set S of candidates for the interval T; and a side information generating encoding the determined interval T to obtain side information. The interval determining determines the interval T from a set S of Y candidates (Y<Z) including Z2 candidates (Z2<Z) selected from among Z candidates for the interval T representable with the side information without depending on a candidate subjected to the interval determination in a previous frame a predetermined number of frames before the current frame and including a candidate subjected to the interval determination in the previous frame the predetermined number of frames before the current frame.

Abstract: Apparatuses, systems, methods, and media for filtering a data stream are provided. The data stream is analyzed based on an acoustic parameter to determine extraneous portions in which a first predetermined condition is satisfied. When a first extraneous portion is separated from a second extraneous portion by a non-extraneous portion in which the first predetermined condition is not satisfied, it is determined whether the first extraneous portion being separated from the second extraneous portion by the non-extraneous portion satisfies a second predetermined condition. At least one of the first extraneous portion and the second extraneous portion is deleted from the data stream to produce a filtered data stream in response to determining the second predetermined condition is satisfied.

Abstract: A voice switching device includes a learning unit configured to learn a background noise model expressing background noise contained in a first voice signal, based on the first voice signal, while the first voice signal having a first frequency band is received; a pseudo noise generation unit configured to generate pseudo noise expressing noise in a pseudo manner, based on the background noise model, after a first time point when the first voice signal is last received in a case where a received voice signal is switched from the first voice signal to a second voice signal having a second frequency band narrower than the first frequency band; and a superimposing unit configured to superimpose the pseudo noise on the second voice signal after the first time point.

Abstract: The invention provides an audio decoder being configured for decoding a bitstream so as to produce therefrom an audio output signal, the bitstream including at least an active phase followed by at least an inactive phase, wherein the bitstream has encoded therein at least a silence insertion descriptor frame which describes a spectrum of a background noise, the audio decoder including: a silence insertion descriptor decoder configured to decode the silence insertion descriptor frame; a decoding device configured to reconstruct the audio output signal from the bitstream during the active phase; a spectral converter configured to determine a spectrum of the audio output signal; a noise estimator device configured to determine a first spectrum of the noise of the audio output signal; a resolution converter configured to establish a second spectrum of the noise of the audio output signal; a comfort noise spectrum estimation device; and a comfort noise generator.

Abstract: Techniques are described for calculating one or more verbal fluency scores for a person. An example method includes classifying, by a computing device, samples of audio data of speech of a person, based on amplitudes of the samples, into a first class of samples including speech or sound and a second class of samples including silence. The method further includes analyzing the first class of samples to determine a number of words spoken by the person, and calculating a verbal fluency score for the person based at least in part on the determined number of words spoken by the person.

Abstract: An electromagnetic interference (EMI) signal is processed by digitizing the EMI signal, generating a plurality of overlapping time records from the digitized EMI signal, applying a window function to the plurality of overlapping time records to produce a plurality of modified time records, wherein the window function has a substantially flat top, and performing a fast Fourier transform (FFT) on each of the modified time records to produce a plurality of corresponding amplitude envelopes.

Abstract: Systems and methods for structuring information include determining information quantity (IQ) and information value (IV) in an original digital information file (ODIF). An initial manipulation process applied to the ODIF forms a first resulting DIF (FRDIF), and a subsequent manipulation process applied to the FRDIF forms a second resulting DIF, wherein each manipulation process removes at least one element of the processed DIF and/or represents an element combination with a representative element and a first indicia of an interrelationship between the representative element and one or more elements in the combination, to reduce the IQ of the processed DIF, while retaining the IV thereof within a threshold. Manipulation processes are successively applied to the previously resulting DIF until successive applications do not achieve a threshold reduction in IQ. The last resulting DIF has a primary structure with a reduced IQ and an IV within the threshold of the original IV.

Abstract: The present disclosure describes a system (100) for reducing background noise from a speech audio signal generated by a user. The system (100) includes a user device (102) receiving the speech audio signal, a noise reduction device (118) in communication with a stored data repository (208), where the noise reduction device is configured to convert the speech audio signal to text; generate synthetic speech based on the converted text; optionally determine the user as an actual subscriber based on a comparison between the speech audio signal with the synthetic speech; and selectively transmit the speech audio signal or the synthetic speech based on comparison between the predicted subjective quality of the recorded speech and the synthetic speech.

Abstract: The present disclosure is directed towards a method for speech intelligibility. The method may include receiving, at one or more computing devices, a first speech input from a first user and performing voice activity detection upon the first speech input. The method may also include analyzing a spectral tilt associated with the first speech input, wherein analyzing includes computing an impulse response of a linear predictive coding (“LPC”) synthesis filter in a linear pulse code modulation (“PCM”) domain and wherein the one or more computing devices includes an adaptive high pass filter configured to recalculate one or more linear prediction coefficients.

Abstract: A frame loss compensation method and apparatus for audio signals are disclosed. The method includes: when a first frame immediately following a correctly received frame is lost, judging a frame type of the first lost frame, and when the first lost frame is a non-multi-harmonic frame, calculating MDCT coefficients of the first lost frame by using MDCT coefficients of one or more frames prior to the first lost frame; obtaining an initially compensated signal of the first lost frame according to the MDCT coefficients of the first lost frame; and performing a first class of waveform adjustment on the initially compensated signal of the first lost frame and taking an adjusted time-domain signal as a time-domain signal of the first lost frame. The apparatus includes a frame type judgment module, an MDCT coefficient acquisition module, an initial compensation signal acquisition module and an adjustment module.

Abstract: A time warp contour calculator for use in an audio signal decoder receives an encoded warp ratio information, derives a sequence of warp ratio values from the encoded warp ratio information, and obtains warp contour node values starting from a time warp contour start value. Ratios between the time warp contour node values and the time warp contour starting value are determined by the warp ratio values. The time warp contour calculator computes a time warp contour node value of a given time warp contour node, on the basis of a product-formation having a ratio between the time warp contour node values of the intermediate time warp contour node and the time warp contour starting value and a ratio between the time warp contour node values of the given time warp contour node and of the intermediate time warp contour node as factors.

Abstract: A new hybrid audio decoder and a new hybrid audio encoder having block switching for speech signals and audio signals are provided. Currently, very low bitrate audio coding methods for speech and audio signals are proposed. These audio coding methods cause very long delays. Generally, in coding an audio signal, an algorithm delay tends to be long to achieve higher frequency resolution. In coding a speech signal, the delay needs to be reduced because the speech signal is used for telecommunication. To balance fine coding quality for speech and audio input signals with very low bitrate, a combination of a low delay filter bank like AAC-ELD and a CELP coding method is provided.

Abstract: This invention provides a voiced sound interval detection device which enables appropriate detection of a voiced sound interval of an observation signal even when a volume of sound from a sound source varies or when the number of sound sources is unknown or when different kinds of microphones are used together.

Abstract: A method and system for frame-level merging of HMM state predictions determined by different techniques is disclosed. An audio input signal may be transformed into a first and second sequence of feature vector, the sequences corresponding to each other and to a temporal sequence of frames of the audio input signal on a frame-by-frame basis. The first sequence may be processed by a neural network (NN) to determine NN-based state predictions, and the second sequence may be processed by a Gaussian mixture model (GMM) to determine GMM-based state predictions. The NN-based and GMM-based state predictions may be merged as weighted sums for each of a plurality of HMM state on a frame-by-frame basis to determine merged state predictions. The merged state predictions may then be applied to the HMMs to speech content of the audio input signal.