37 results about "VOCAL PARAMETERS" patented technology

The invention is suitable for the technical field of information and provides a good friend recommendation method and apparatus. The method comprises: obtaining audio information of a user, obtaining values of N types of sound parameters from the audio information, and obtaining N reference values corresponding to the N types of sound parameters, wherein N is an integer greater than or equal to 1; comparing the values of the N type of sound parameters with the N reference values respectively to obtain first comparison results; according to the first comparison results, determining emotion information of the user; and according to the emotion information of the user, recommending good friends for the user. According to the good friend recommendation method and apparatus, the emotion of the user is considered when the good friends are recommended for the user, and the good friends with the same emotion are quickly found for the user, so that the flexibility of good friend recommendation is improved.

A low power sound recognition sensor is configured to receive an analog signal that may contain a signature sound. Sound parameter information is extracted from the analog signal and compared to a sound parameter reference stored locally with the sound recognition sensor to detect when the signature sound is received in the analog signal. A trigger signal is generated when a signature sound is detected. A portion of the extracted sound parameter information is sent to a remote training location for adaptive training when a signature sound detection error occurs. An updated sound parameter reference from the remote training location is received in response to the adaptive training.

A system and method are provided for processing sound signals. The processing may include identifying individual harmonic sounds represented in sound signals, determining sound parameters of harmonic sounds, classifying harmonic sounds according to source, and / or other processing. The processing may include transforming the sound signals (or portions thereof) into a space which expresses a transform coefficient as a function of frequency and chirp rate. This may facilitate leveraging of the fact that the individual harmonics of a single harmonic sound may have a common pitch velocity (which is related to the chirp rate) across all of its harmonics in order to distinguish an the harmonic sound from other sounds (harmonic and / or non-harmonic) and / or noise.

In embodiments of the present invention improved capabilities are described for a computer-based method for reproducing an acoustic environment including accessing a computer stored multi-dimensional sound profile of a first space, wherein the multi-dimensional sound profile of the first space includes at least one multi-dimensional sound signature, the at least one multi-dimensional sound signature comprising a time-based sound reflection sequence within the first space for at least two sound parameters; and modifying a characteristic of an array of speakers in a second space to change the multi-dimensional sound profile in the second space to resemble at least one characteristic of the computer stored multi-dimensional sound profile of the first space.

A system and method may be configured to process audio signals. The systems and methods may track pitch, FM slope, and / or harmonic envelopes on the audio signal, may reconstruct sounds represented in the audio signal, and / or may analyze the audio signal. segment or category. The audio signal may be transformed such that the audio signal is transformed into a frequency-modulated domain that enhances sound parameter tracking, reconstruction and / or classification.

The embodiment of the invention discloses a recording method, device, equipment and storage medium. Wherein, the method is performed by including at least two audio collection devices, including: acquiring the collected first sound signal, and determining the first sound signal as the main sound source according to a preset standard; each of the at least two audio collection devices The second sound signal collected by the audio collection device is compared with the main sound source to determine the main signal in the second sound signal; according to the sound parameters of the main signal in the second sound signal in each audio collection device, determine at least two The main audio collection device and the secondary audio collection device in the two audio collection devices use the main audio collection device for sound recording, and use the secondary audio collection device for noise reduction processing. By determining the main sound source, comparing the voice with the main sound source to obtain the main signal, and determining the main-sub-relationship of the audio collection equipment, it will play a corresponding role and improve the accuracy of the judgment of the main signal and the clarity of the recording.

Systems and methods for detection, classification, and diagnosis of vocal anomalies in vocal streams are disclosed. Discussed are a method for generating a biometric voiceprint for analyzing user vocal streams to detect and classify vocal anomalies and a method for notifying the appropriate party, where the notification is based on the diagnosis reported by the system. Manual classification in the event of automatic classification failure is discussed, where the manual classification data can be used as training data to improve the functionality of the classification model.