Abstract: A classification training system for binary and multi-class classification comprises a neural network operable to perform classification of input data, a training dataset including pre-segmented, labeled training samples, and a classification training module operable to train the neural network using the training dataset. The classification training module includes a forward pass processing module, and a backward pass processing module. The backward pass processing module is operable to determine whether a current frame is in a region of target (ROT), determine ROT information such as beginning and length of the ROT and update weights and biases using a cross-entropy cost function and connectionist temporal classification cost function. The backward pass module further computes a soft target value using ROT information and computes a signal output error using the soft target value and network output value.

Abstract: A classification system and method for training a neural network includes receiving a stream of segmented, labeled training data having a sequence of frames, computing a stream of input features data for the sequence of frames, and generating neural network outputs for the sequence of frames in a forward pass through the training data and in accordance weights and biases. The weights and biases are updated in a backward pass through the training data, including determining Region of Target (ROT) information from the segmented, labeled training data, computing modified forward and backward variables based on the neural network outputs and the ROT information, deriving a signal error for each frame within the sequence of frames based on the modified forward and backward variables, and updating the weights and biases based on the derived signal error. An adaptive learning module is provided to improve a convergence rate of the neural network.

Abstract: Methods for processing a multichannel audio signal that includes transient noise signals are provided. The method includes buffering the multichannel audio signal in a subband domain, and estimating the subband frames for transient noise likelihood. A probability of transient noise for the buffered subband frames is determined and a multichannel spatial filter is applied to decompose the subband frames to transient attenuated target source and noise estimation cancelled of the target source signal. A spectral filter is applied to the target source frame to enhance the target source frame and the subband frames that are determined to have a probability of the transient noise greater than a first threshold and a probability of target source less than a second threshold are muted.

Abstract: A method for echo cancellation in multichannel audio signals includes receiving a plurality of time-domain signals, including multichannel audio signals and at least one reference signal, transforming the time-domain signals to K under-sampled complex-valued subband signals using an analysis filter bank. A probability of acoustic echo dominance is produced using a single-double talk estimator, and a multichannel source separation is performed based on the probability to decompose the audio signals into a near-end source signal and a residual echoes using source separation. The residual echo components are removed from the near-end source signal using a spectral filter bank, and the subband audio signals are reconstructed to a multichannel time-domain audio signal using a subband synthesis filter.

Abstract: Audio signal processing for adaptive de-reverberation uses a least mean squares (LMS) filter that has improved convergence over conventional LMS filters, making embodiments practical for reducing the effects of reverberation for use in many portable and embedded devices, such as smartphones, tablets, laptops, and hearing aids, for applications such as speech recognition and audio communication in general. The LMS filter employs a frequency-dependent adaptive step size to speed up the convergence of the predictive filter process, requiring fewer computational steps compared to a conventional LMS filter applied to the same inputs. The improved convergence is achieved at low memory consumption cost. Controlling the updates of the prediction filter in a high non-stationary condition of the acoustic channel improves the performance under such conditions. The techniques are suitable for single or multiple channels and are applicable to microphone array processing.

Abstract: Systems and methods for processing multichannel audio signals include receiving a multichannel time-domain audio input, transforming the input signal to plurality of multi-channel frequency domain, k-spaced under-sampled subband signals, buffering and delaying each channel, saving a subset of spectral frames for prediction filter estimation at each of the spectral frames, estimating a variance of the frequency domain signal at each of the spectral frames, adaptively estimating the prediction filter in an online manner using a recursive least squares (RLS) algorithm, linearly filtering each channel using the estimated prediction filter, nonlinearly filtering the linearly filtered output signal to reduce residual reverberation and the estimated variances, producing a nonlinearly filtered output signal, and synthesizing the nonlinearly filtered output signal to reconstruct a dereverberated time-domain multi-channel audio signal.

Abstract: A method for echo cancellation in multichannel audio signals includes receiving a plurality of time-domain signals, including multichannel audio signals and at least one reference signal, transforming the time-domain signals to K under-sampled complex-valued subband signals using an analysis filter bank. A probability of acoustic echo dominance is produced using a single-double talk estimator, and a multichannel source separation is performed based on the probability to decompose the audio signals into a near-end source signal and a residual echoes using source separation. The residual echo components are removed from the near-end source signal using a spectral filter bank, and the subband audio signals are reconstructed to a multichannel time-domain audio signal using a subband synthesis filter.

Abstract: A method for echo cancellation in multichannel audio signals includes receiving a plurality of time-domain signals, including multichannel audio signals and at least one reference signal, transforming the time-domain signals to K under-sampled complex-valued subband signals using an analysis filter bank, and performing, for each of the K under-sampled complex-value subband signals, linear echo cancellation of the reference signal from each channel using an acoustic echo canceller. A probability of acoustic echo dominance is produced using a single-double talk estimator, and a semi-blind multichannel source separation is performed based on the probability and independent component analysis (“ICA”) to decompose the audio signals into a near-end source signal and a residual echoes using subband semi-blind source separation.

Abstract: A selective audio source enhancement system includes a processor and a memory, and a pre-processing unit configured to receive audio data including a target audio signal, and to perform sub-band domain decomposition of the audio data to generate buffered outputs. In addition, the system includes a target source detection unit configured to receive the buffered outputs, and to generate a target presence probability corresponding to the target audio signal, as well as a spatial filter estimation unit configured to receive the target presence probability, and to transform frames buffered in each sub-band into a higher resolution frequency-domain. The system also includes a spectral filtering unit configured to retrieve a multichannel image of the target audio signal and noise signals associated with the target audio signal, and an audio synthesis unit configured to extract an enhanced mono signal corresponding to the target audio signal from the multichannel image.

Abstract: Methods for processing a multichannel audio signal that includes transient noise signals are provided. The method includes buffering the multichannel audio signal in a subband domain, and estimating the subband frames for transient noise likelihood. A probability of transient noise for the buffered subband frames is determined and a multichannel spatial filter is applied to decompose the subband frames to transient attenuated target source and noise estimation cancelled of the target source signal. A spectral filter is applied to the target source frame to enhance the target source frame and the subband frames that are determined to have a probability of the transient noise greater than a first threshold and a probability of target source less than a second threshold are muted.

Abstract: Various techniques are provided to perform enhanced automatic speech recognition. For example, a subband analysis may be performed that transforms time-domain signals of multiple audio channels in subband signals. An adaptive configurable transformation may also be performed to produce single or multichannel-based features whose values are correlated to an Ideal Binary Mask (IBM). An unsupervised Gaussian Mixture Model (GMM) model fitting the distribution of the features and producing posterior probabilities may also be performed, and the posteriors may be combined to produce deep neural network (DNN) feature vectors. A DNN may be provided that predicts oracle spectral gains from the input feature vectors. Spectral processing may be performed to produce an estimate of the target source time-frequency magnitudes from the mixtures and the output of the DNN. Subband synthesis may be performed to transform signals back to time-domain.

Abstract: A selective audio source enhancement system includes a processor and a memory, and a pre-processing unit configured to receive audio data including a target audio signal, and to perform sub-band domain decomposition of the audio data to generate buffered outputs. In addition, the system includes a target source detection unit configured to receive the buffered outputs, and to generate a target presence probability corresponding to the target audio signal, as well as a spatial filter estimation unit configured to receive the target presence probability, and to transform frames buffered in each sub-band into a higher resolution frequency-domain. The system also includes a spectral filtering unit configured to retrieve a multichannel image of the target audio signal and noise signals associated with the target audio signal, and an audio synthesis unit configured to extract an enhanced mono signal corresponding to the target audio signal from the multichannel image.

Abstract: A system for processing audio data comprising a linear demixing system configured to receive a plurality of sub-band audio channels and to generate an audio output and a noise output. A spatial likelihood system coupled to the linear demixing system, the spatial likelihood system configured to receive the audio output and the noise output and to generate a spatial likelihood function. A sequential Gaussian mixture model system coupled to the spatial likelihood system, the sequential Gaussian mixture model system configured to generate a plurality of model parameters. A Bayesian probability estimator system configured to receive the plurality of model parameters and a speech/noise presence probability and to generate a noise power spectral density and spectral gains. A spectral filtering system configured to receive the spectral gains and to apply the spectral gains to noisy input mixtures.

Abstract: A system for processing audio data comprising a linear demixing system configured to receive a plurality of sub-band audio channels and to generate an audio output and a noise output. A spatial likelihood system coupled to the linear demixing system, the spatial likelihood system configured to receive the audio output and the noise output and to generate a spatial likelihood function. A sequential Gaussian mixture model system coupled to the spatial likelihood system, the sequential Gaussian mixture model system configured to generate a plurality of model parameters. A Bayesian probability estimator system configured to receive the plurality of model parameters and a speech/noise presence probability and to generate a noise power spectral density and spectral gains. A spectral filtering system configured to receive the spectral gains and to apply the spectral gains to noisy input mixtures.

Abstract: A method for echo cancellation in multichannel audio signals includes receiving a plurality of time-domain signals, including multichannel audio signals and at least one reference signal, transforming the time-domain signals to K under-sampled complex-valued subband signals using an analysis filter bank, and performing, for each of the K under-sampled complex-value subband signals, linear echo cancellation of the reference signal from each channel using an acoustic echo canceller. A probability of acoustic echo dominance is produced using a single-double talk estimator, and a semi-blind multichannel source separation is performed based on the probability and independent component analysis (“ICA”) to decompose the audio signals into a near-end source signal and a residual echoes using subband semi-blind source separation.

Abstract: A selective audio source enhancement system includes a processor and a memory, and a pre-processing unit configured to receive audio data including a target audio signal, and to perform sub-band domain decomposition of the audio data to generate buffered outputs. In addition, the system includes a target source detection unit configured to receive the buffered outputs, and to generate a target presence probability corresponding to the target audio signal, as well as a spatial filter estimation unit configured to receive the target presence probability, and to transform frames buffered in each sub-band into a higher resolution frequency-domain. The system also includes a spectral filtering unit configured to retrieve a multichannel image of the target audio signal and noise signals associated with the target audio signal, and an audio synthesis unit configured to extract an enhanced mono signal corresponding to the target audio signal from the multichannel image.