Abstract: Method of speech enhancement using Neural Network-based combined signal starts with training neural network offline which includes: (i) exciting at least one accelerometer and at least one microphone using training accelerometer signal and training acoustic signal, respectively. The training accelerometer signal and the training acoustic signal are correlated during clean speech segments. Training neural network offline further includes (ii) selecting speech included in the training accelerometer signal and in the training acoustic signal, and (iii) spatially localizing the speech by setting a weight parameter in the neural network based on the selected speech included in the training accelerometer signal and in the training acoustic signal. The neural network that is trained offline is then used to generate a speech reference signal based on an accelerometer signal from the at least one accelerometer and an acoustic signal received from the at least one microphone. Other embodiments are described.

Abstract: Method of speech enhancement using Neural Network-based combined signal starts with training neural network offline which includes: (i) exciting at least one accelerometer and at least one microphone using training accelerometer signal and training acoustic signal, respectively. The training accelerometer signal and the training acoustic signal are correlated during clean speech segments. Training neural network offline further includes (ii) selecting speech included in the training accelerometer signal and in the training acoustic signal, and (iii) spatially localizing the speech by setting a weight parameter in the neural network based on the selected speech included in the training accelerometer signal and in the training acoustic signal. The neural network that is trained offline is then used to generate a speech reference signal based on an accelerometer signal from the at least one accelerometer and an acoustic signal received from the at least one microphone. Other embodiments are described.

Abstract: An echo canceller can be arranged to receive an input signal and to receive a reference signal. The echo canceller can subtract a linear component of the reference signal from the input signal. A noise suppressor can suppress non-linear effects of the reference signal in the input signal in correspondence with a large number of selectable parameters. Such suppression can be provided on a frequency-by-frequency basis, with a unique set of tunable parameters selected for each frequency. A degree of suppression provided by the noise suppressor can correspond to an estimate of residual echo remaining after the one or more linear components of the reference signal have been subtracted from the input signal, to an estimated double-talk probability, and to an estimated signal-to-noise ratio of near-end speech in the input signal for each respective frequency. A speech recognizer can receive a processed input signal from the noise suppressor.

Abstract: An echo canceller can be arranged to receive an input signal and to receive a reference signal. The echo canceller can subtract a linear component of the reference signal from the input signal. A noise suppressor can suppress non-linear effects of the reference signal in the input signal in correspondence with a large number of selectable parameters. Such suppression can be provided on a frequency-by-frequency basis, with a unique set of tunable parameters selected for each frequency. A degree of suppression provided by the noise suppressor can correspond to an estimate of residual echo remaining after the one or more linear components of the reference signal have been subtracted from the input signal, to an estimated double-talk probability, and to an estimated signal-to-noise ratio of near-end speech in the input signal for each respective frequency. A speech recognizer can receive a processed input signal from the noise suppressor.

Abstract: Customizable layout of search results techniques are described. In an implementation, a user interface to display search results is provided having one or more portions that are user selectable to customize a layout of search results from a search service. When one or more of the portions are selected, the layout is customized by corresponding rearrangement of obtained search results locally at a client. One or more preferences that describe the layout specified by the user may be stored based on the user's interaction with the user interface. When the user performs a search via the search service, the results of the search are presented in accordance with the layout specified by the user.

Abstract: Customizable layout of search results techniques are described. In an implementation, a user interface to display search results is provided having one or more portions that are user selectable to customize a layout of search results from a search service. When one or more of the portions are selected, the layout is customized by corresponding rearrangement of obtained search results locally at a client. One or more preferences that describe the layout specified by the user may be stored based on the user's interaction with the user interface. When the user performs a search via the search service, the results of the search are presented in accordance with the layout specified by the user.

Abstract: A system, a method and computer-readable media for personalizing a user search. Information is maintained that indicates a set of content selected by a user. A search macro is generated by utilizing this information. A user input defining a search query is received, and the search macro is utilized to further define the search query.