Abstract:
Laser-based system and optical microphone having increased bandwidth. The system includes a laser microphone to transmit a laser beam towards a human speaker; to receive an optical feedback signal reflected back from the human speaker; and to perform self-mixing interferometry. An optical feedback signal bandwidth enhancer improves the bandwidth of the optical feedback signal, to improve the quality of remote speech detection that is based on the optical feedback signal. The bandwidth enhancement utilizes takes into account one or more of: the identity of the face-region hit by the laser beam; the skin color or shade; obstruction of the skin by hair or by accessories; ability to allocate increased processing resources for processing of the optical feedback signal; ability to modify modulation frequency of the optical feedback signal; Signal to Noise Ratio (SNR) estimation; bandwidth estimation; acoustic-optical transmission channel estimation; or other suitable parameters.
Abstract:
System and techniques for automatic tuning of speech recognition parameters are described herein. A clean audio segment and a dirty audio segment may be obtained, in an iterative fashion, optimized preprocessing parameters may be obtained by, at an iteration, selecting a set of parameters, preprocessing the clean audio segment with the set of parameters to produce a first result, preprocessing the dirty audio segment with the set of parameters to produce a second result, and scoring a portion of the first result with the a corresponding portion of the second result using clean-diff. When an optimization threshold is reached, exit the iterative process and provide the set of parameters from the last iteration.
Abstract:
Die Erfindung betrifft ein Verfahren sowie ein Sprechfunksystem zur Identifikation und Prüfung von Sprechfunkmeldungen (M 1 ...M 3 ) sowie zur Zuordnung von Sprechfunkmeldungen (M 1 ...M 3 ) zu Fahrzeugen (F 1 ...F 3 ), wobei jeweils ein Sprecher an einer vorgegebenen Stelle jeder Sprechfunkmeldung (M 1 ...M 3 ) die Kennung (K) angibt. Erfindungsgemäß ist vorgesehen, dass a) eine Anzahl von abgegebenen Sprechfunkmeldungen (M 1 ...M 3 ) aufgezeichnet wird, wobei jeweils die in der Sprechfunkmeldung (M 1 ...M 3 ) enthaltene Kennung (K) mittels Spracherkennung (0) in eine digitale Kennung (K d ) transformiert wird, wobei aus denjenigen Sprechfunkmeldungen (M 1 ...M 3 ), denen jeweils dieselbe digitale Kennung zugewiesen wurde, ein Biometrie-Datensatz (B 1 ...B 3 ) extrahiert wird, und wobei dieser Biometrie-Datensatz (B 1 ...B 3 ) der jeweiligen digitalen Kennung (K d ) zugewiesen wird, und b) danach eine weitere Sprechfunkmeldung (M 4 ) aufgezeichnet wird, wobei aus der weiteren Sprechfunkmeldung (M 4 ), ein weiterer Biometrie-Datensatz (B 4 ) extrahiert wird, wobei unter den abgespeicherten Biometrie-Datensätzen (B 1 ...B 3 )) nach demjenigen Biometrie-Datensatz (B 1 ) gesucht wird, der mit dem weiteren Biometrie-Datensatz (B 4 ) am besten übereinstimmt und die Sprechfunkmeldung (M 4 ) demjenigen Fahrzeug (F 1 ) mit der diesem Biometrie-Datensatz (B 1 ) zugeordneten Kennung (K d ) zugeordnet wird.
Abstract:
A system, method and program product for improved techniques for sound management and sound localization is provided. The present invention provides for improving sound localization and detection by inputting a predetermined location's dimensional data and location reference and processing detected sound details, detection device details and the associated location dimensional data as sound localization information for multi-dimensional display. The present invention provides mapping information of sound, people and structural information for use in multiple applications including residential, commercial and emergency situations.
Abstract:
An electronic device includes a microphone (108) that receives an audio signal, and a processor that is electrically coupled to the microphone (108). The processor (204, 300) detects a trigger phrase in the received audio signal and measure characteristics of the detected trigger phrase. Based on the measured characteristics of the detected trigger phrase, the processor (204,300) determines whether the detected trigger phrase is valid.
Abstract:
The disclosure is directed to pre-processing audio signals. In one implementation, an electronic device (102) receives an audio signal that has audio information, obtains auxiliary information (such as location, velocity, direction, light, proximity of objects, and temperature), and determines, based on the audio information and the auxiliary information, a type of audio environment in which the electronic device (102) is operating. The device (102) selects an audio pre-processing procedure based on the determined audio environment type and pre-processes the audio signal according to the selected pre-processing procedure. The device (102) may then perform speech recognition on the pre-processed audio signal.