University of Washington

The Boeing Company

Erudite Inc.

Les Atlas

Charles Pascal Clark

Stephen G Dame

Jeffrey Kenneth Thompson

Patrick J McVittie

Jay T Rubinstein

Paul Henry Willms

Mark S Vinton

Kaibao Nie

Xing Li

Speech detection can be achieved by identifying a speech segment within an audio segment using image classification. An audio segment of radio communications is obtained. An audio sub-segment within the audio segment is extracted. A sampled histogram is generated of a plurality of sampled values across a sampled time window of the audio sub-segment. A two-dimensional image is generated that represents a two-dimensional mapping of the sampled histogram along a first dimension and a predefined histogram along a second dimension that is orthogonal to the first dimension. The two-dimensional image is provided to an image classifier previously trained using the predefined histogram. An output is received from the image classifier based on the two-dimensional image. The output indicates whether the audio sub-segment contains speech.

Speech detection using image classification

Objects in a cargo shipping container are detected by measuring vibration resonant frequency peaks of the container. The mass of an object on the floor of the container effects the vibration resonance of the container, enabling the object to be detected. A vibration source and a plurality of accelerometers are either attached to the steel structure of the container, or are disposed on a supporting structure, such as a cargo crane or lift, so that they contact the container. The vibration source causes the container to vibrate, and the accelerometers detect the vibration resonance of the container. A mismatch between a cargo manifest and an observed cargo, or detection of an object having relatively high mass, e.g., due to lead shielding, can justify a manual inspection. The process uses synchronous processing to achieve the sensitivity needed, is unobtrusive, and does not slow the flow of cargo through a facility.

Detecting objects in shipping containers by vibration spectral analysis

A method and system for optimally repairing a clipped audio signal. Clipping occurs when a waveform exceeds a dynamic range of a recording device. Portions of an audio signal exceeding the dynamic range or saturation level of the recording device are clipped, causing distortion when the clipped recorded signal is played. To address this problem, successive frames of the clipped audio data are repaired to fill in gaps where the data were clipped. For each frame, an iterative process repetitively estimates an auto-covariance and detects clipped samples in the frame or a sub-frame in order to compute a least-squares solution for the frame that interpolates the clipped data. The process can cause inverted peaks in the repaired data, which must then be rectified to produced corrected repaired data. The corrected repaired data for the successive frames are recombined using interpolation, to produce a complete repaired audio data set.

Clipped-waveform repair in acoustic signals using generalized linear prediction

The restoration of melody perception is a key remaining challenge in cochlear implants. A novel sound coding strategy is proposed that converts an input audio signal into time-varying electrically stimulating pulse trains. A sound is first split into several frequency sub-bands with a fixed filter bank or a dynamic filter bank tracking harmonics in sounds. Each sub-band signal is coherently downward shifted to a low-frequency base band. These resulting coherent envelope signals have Hermitian symmetric frequency spectrums and are thus real-valued. A peak detector or high-rate sampler of half-wave rectified coherent envelope signals in each sub-band further converts the coherent envelopes into rate-varying, interleaved pulse trains. Acoustic simulations of cochlear implants using this new technique with normal hearing listeners, showed significant improvement in melody recognition over the most common conventional stimulation approach used in cochlear implants.

Enhanced signal processing for cochlear implants

A method for identifying at least one nuclear threat to homeland security, wherein such each nuclear threat is either hidden inside at least one cargo container before transit, or is placed inside at least one cargo container while in transit. Each such nuclear threat while interacting with its surroundings generates a unique nuclear threat signature. The method comprises: (A) detecting at least one nuclear threat signature; (B) measuring a background nuclear threat signature distribution in a nuclear threat-free environment; (C) comparing each detected nuclear threat signature with the background nuclear threat signature distribution; (D) if deviation of the detected nuclear threat signature from the background nuclear threat signature distribution is statistically significant, selecting the detected nuclear threat signature to be a part of an array of statistically significant detected nuclear threat signatures; and (E) substantially continuously processing the array of selected statistically significant detected nuclear threat signatures in order to determine a likelihood of each such nuclear threat.

Detection of nuclear materials hidden inside cargo shipments by using sensor fusion technique

The speech of two or more simultaneous speakers (or other simultaneous sounds) conveyed in a single channel are distinguished. Joint acoustic/modulation frequency analysis and display tools are used to localize and separate sonorant portions of multiple-speakers' speech into distinct regions using invertible transform functions. For example, the regions representing one of the speakers are set to zero, and the inverted modified display maintains only the speech of the other speaker. A combined audio signal is manipulated using a base acoustic transform, followed by a second modulation transform, which separates the combined signals into distinguishable components. The components corresponding to the undesired speaker are masked, leaving only the second modulation transform of the desired speaker's audio signal. An inverse second modulation transform of the desired signal is performed, followed by an inverse base acoustic transform of the desired signal, providing an audio signal for only the desired speaker.

Single channel sound separation

A method and system for encoding and decoding an input signal in relation to the most perceptually relevant aspects of the input signal. A two-dimensional (2D) transform is applied to the input signal to produce a magnitude matrix and a phase matrix that can be inverse quantized by a decoder. A first column of coefficients of the magnitude matrix represents a mean spectral density (MSD) function of the input signal. Relevant aspects of the MSD function are encoded at a beginning of a data packet. The MSD function is also processed through a core perception model to determine bit allocation. The matrices are then quantized and priority ordered into a data packet, with the least perceptually relevant information at the end of the packet so that it may be ignored or truncated for scalability to the channel data rate capacity.

Growing community of inventors

Seattle, WA, United States of America

Les Atlas