Abstract: A method of capturing speech using a television system comprising a microphone device and a playback device. A playback device of the television system plays a tv audio signal to generate acoustic tv audio and a microphone of the television system captures a speech audio signal comprising a mixture of speech from a user and the acoustic tv audio. The method obtains a representation of the tv audio signal that lacks a well-defined synchronization with the tv audio signal and processes the speech audio signal using a semi-blind source separation process to separate the speech from the user from the acoustic tv audio.

Abstract: A method of cropping a portion of an audio signal captured from a plurality of spatially separated audio sources in a scene, the method comprising: capturing the audio signal with one or more recording devices; separating the audio signal into a plurality of components each associated with one or more of the plurality of audio sources; selecting a spatial region in the scene; determining which of the plurality of components are associated with an audio source positioned outside of the selected spatial region; and cropping the plurality of components associated with an audio source positioned outside of the selected spatial region out of the audio signal.

Abstract: A method for acoustic source separation comprises inputting acoustic data from a plurality of acoustic sensors, combined from a plurality of acoustic sources, converting the acoustic data to time-frequency domain data comprising time-frequency data frames, and constructing a multichannel filter for the time-frequency data frames to separate signals from the acoustic sources. The constructing comprises determining a set of de-mixing matrices (Wf) to apply to each time-frequency data frame to determine a vector of separated outputs (yft) by modifying each of the de-mixing matrices by a respective gradient value (G;G?) for a frequency dependent upon a gradient of a cost function measuring a separation of the sources by the respective de-mixing matrix. The respective gradient values for each frequency are each calculated from a stochastic selection of the time-frequency data frames.

Abstract: A method of cropping a portion of an audio signal captured from a plurality of spatially separated audio sources in a scene, the method comprising: capturing the audio signal with one or more recording devices; separating the audio signal into a plurality of components each associated with one or more of the plurality of audio sources; selecting a spatial region in the scene; determining which of the plurality of components are associated with an audio source positioned outside of the selected spatial region; and cropping the plurality of components associated with an audio source positioned outside of the selected spatial region out of the audio signal.

Abstract: A method for acoustic source separation comprises inputting acoustic data from a plurality of acoustic sensors, combined from a plurality of acoustic sources, converting the acoustic data to time-frequency domain data comprising time-frequency data frames, and constructing a multichannel filter for the time-frequency data frames to separate signals from the acoustic sources. The constructing comprises determining a set of de-mixing matrices (Wf) to apply to each time-frequency data frame to determine a vector of separated outputs (yft) by modifying each of the de-mixing matrices by a respective gradient value (G;G?) for a frequency dependent upon a gradient of a cost function measuring a separation of the sources by the respective de-mixing matrix. The respective gradient values for each frequency are each calculated from a stochastic selection of the time-frequency data frames.

Abstract: We describe a method of blind source separation for use, for example, in a listening or hearing aid. The method processes input data from multiple microphones each receiving a mixed signal from multiple audio sources, performing independent component analysis (ICA) on the data in the time-frequency domain based on an estimation of a spectrogram of each acoustic source. The spectrograms of the sources are determined from non-negative matrix factorization (NMF) models of each source, the NMF model representing time-frequency variations in the output of an acoustic source in the time-frequency domain. The NMF and ICA models are jointly optimized, thus automatically resolving an inter-frequency permutation ambiguity.

Abstract: We describe techniques for restoring an audio signal. In embodiments these employ masked positive semi-definite tensor factorization to process the signal in the time-frequency domain. Broadly speaking the methods estimate latent variables which factorize a tensor representation of the (unknown) variance/covariance of an input audio signal, using a mask so that the audio signal is separated into desired and undesired audio source components. In embodiments a masked positive semi-definite tensor factorization of ?ftk=MftkUfkVtk is performed, where M defines the mask and U, V the latent variables. A restored audio signal is then constructed by modifying the input signal to better match the variance/covariance of the desired components.

Abstract: A sampled digital audio signal is displayed on a spectrogram, in terms of frequency vs. time. An unwanted noise in the signal is visible in the spectrogram and the portion of the signal containing the unwanted noise can be selected using time and frequency constraints. An estimate for the signal within the selected portion is then interpolated on the basis of desired portions of the signal outside the time constraints defining the selected portion.

Abstract: A sampled digital audio signal is displayed on a spectrogram, in terms of frequency vs. time. An unwanted noise in the signal is visible in the spectrogram and the portion of the signal containing the unwanted noise can be selected using time and frequency constraints. An estimate for the signal within the selected portion is then interpolated on the basis of desired portions of the signal outside the time constraints defining the selected portion. The interpolated estimate can then be used to attenuate or remove the unwanted sound.