-
11.发明授权公开(公告)号：US11327710B2
公开(公告)日：2022-05-10
申请号：US16832883
申请日：2020-03-27
申请人： Adobe Inc.
发明人： Nico Becherer , Sven Duwenhorst
摘要： A computer-implemented method for audio signal processing includes analyzing a foreground audio signal to determine metrics corresponding to audio slices of the foreground audio signal. Each such metric indicates a value for an audio property of a respective audio slice. The method further includes computing a total metric for an audio slice as a function of a set of the metrics corresponding to a set of the audio slices including the audio slice. The method further includes adding a key frame to a track based on the total metric. The track includes the foreground audio signal and a background audio signal, and a location of the key frame corresponds to a location of the audio slice on the track. The key frame indicates a change to the audio property of the background audio signal at the location on the track, and the key frame is utilizable for audio ducking.
-
公开(公告)号：US11322172B2
公开(公告)日：2022-05-03
申请号：US15611754
申请日：2017-06-01
IPC分类号： G10L25/51 , G06Q10/10 , H04M3/51 , G06Q30/00 , G09B19/04 , G10L25/90 , G10L25/48 , G10L15/26
摘要： Computer-generated feedback directed to whether user speech input meets subjective criteria is provided through the evaluation of multiple speaking traits. Initially, discrete instances of various multiple speaking traits are detected within the user speech input provided. Such multiple speaking traits include vocal fry, tag questions, uptalk, filler sounds and hedge words. Audio constructs indicative of individual instances of speaking traits are isolated and identified from appropriate samples. Speaking trait detectors then utilize such audio constructs to identify individual instances of speaking traits within the spoken input. The resulting quantities are scored based on reference to predetermined threshold quantities. The individual speaking trait scores are then amalgamated utilizing a weighting that is derived based on empirical relationships between those speaking traits and the criteria for which the user's speech input is being evaluated. Further adjustments thereof can be made by separately, manually weighting the previously determined quantities.
-
公开(公告)号：US11277518B2
公开(公告)日：2022-03-15
申请号：US16640169
申请日：2018-09-27
发明人： Kai Li , David Gunawan , Feng Deng , Qianqian Fang
摘要： The disclosed teleconferencing methods involve detecting a howl state during a teleconference which involves two or more teleconference client locations and a teleconference server. The teleconference server is configured for providing full-duplex audio connectivity between the teleconference client locations. The howl state is a state of acoustic feedback involving two or more teleconference devices in a teleconference client location. Detecting the howl state involves an analysis of both spectral and temporal characteristics of teleconference audio data. The disclosed teleconferencing methods involve determining which client location is causing the howl state and involve mitigating the howl state or sending a howl state detection message.
-
公开(公告)号：US20220070290A1
公开(公告)日：2022-03-03
申请号：US17522230
申请日：2021-11-09
申请人： HigherGround, Inc.
摘要： Systems, devices, and methods including: capturing, by a capture device, an audio and corresponding location metadata associated with an emergency call; refining the location metadata to provide a refined location metadata; correlating, by the capture device, the refined location metadata of the emergency call with a geofenced location of the computing devices of one or more first responders (FRs); screening, by the capture device or the computing device, the emergency call data; transmitting, by the capture device, a first signal to the one or more computing devices based on the correlation, the transmitted signal including a portion of the captured audio and corresponding location metadata; receiving, by the capture device, an accept signal from the one or more computing devices of one or more FRs; transmitting, by the capture device, a second signal to the one or more computing devices based on the received accept signal.
-
公开(公告)号：US20220036913A1
公开(公告)日：2022-02-03
申请号：US16943250
申请日：2020-07-30
摘要： A system determines an event location of an event within an indoor environment based on an event sound generated by the event. The system employs time-reversal techniques based on a received event sound to identify the event location as being in the vicinity of one of a plurality of locator devices at locator locations in the environment. The system includes a base array located within the environment that receives an indication that an event has been detected. Upon receiving the event sound, the system generates a time-reversed event sound for each transceiver and transmits via each transceiver the time-reversed event sound for that transceiver. When a locator device receives a time-reversed event sound, the locator device determines whether the event is in the vicinity of that locator location of the locator device and, if so, outputs an indication that the event occurred at that locator location.
-
公开(公告)号：US20220028409A1
公开(公告)日：2022-01-27
申请号：US17004015
申请日：2020-08-27
发明人： Chuan-Yu CHANG , Jun-Ying LI
摘要： A method for correcting infant crying identification includes the following steps: a detecting step provides an audio unit to detect a sound around an infant to generate a plurality of audio samples. A converting step provides a processing unit to convert the audio samples to generate a plurality of audio spectrograms. An extracting step provides a common model to extract the audio spectrograms to generate a plurality of infant crying features. An incremental training step provides an incremental model to train the infant crying features to generate an identification result. A judging step provides the processing unit to judge whether the identification result is correct according to a real result of the infant. When the identification result is different from the real result, an incorrect result is generated. A correcting step provides the processing unit to correct the incremental model according to the incorrect result.
-
公开(公告)号：US11227681B2
公开(公告)日：2022-01-18
申请号：US16359339
申请日：2019-03-20
发明人： Allan Wilson , Michael Petersen , Dean Brotzel
摘要： There is provided a device for monitoring the use of a blister package, strip package, vial or bottle contents at a distance. A processor is connected to a compact random or quasi-random n-microphone array and is programmed to detect the sound of the content being expelled from a blister cavity, strip package, or a cap being removed from a vial or bottle. A content use data memory associated with the processor stores information relating to the expulsion or removal events. The processor is equipped with statistical means for differentiating the sound of the content being expelled, from the background noise, generating an electrical signal that is analyzed for relevance to content use events by the processor, and storing the resulting use data in memory. The processor may have an adaptive beam focussing algorithm to determine the direction of the source of the sound.
-
公开(公告)号：US11200909B2
公开(公告)日：2021-12-14
申请号：US16557159
申请日：2019-08-30
发明人： Chen-Yu Chiang , Guan-Ting Liou , Yih-Ru Wang , Sin-Horng Chen
摘要： A method is disclosed. The proposed method includes: providing an initial speech corpus including plural utterances; based on a condition of maximum a posteriori (MAP), according to respective sequences of syllable duration, syllable duration prosodic state, syllable tone, base-syllable type, and break type of the kth utterance, using a probability of an ISR of the kth utterance xk to estimate an estimated value {circumflex over (x)}k of the xk; and through the MAP condition, according to respective sequences of syllable duration, syllable duration prosodic state, syllable tone, base-syllable type, and break type of the given lth breath group/prosodic phrase group (BG/PG) of the kth utterance, using a probability of an ISR of the lth BG/PG of the kth utterance xk,l to estimate an estimated value {circumflex over (x)}k,l of the xk,l wherein the {circumflex over (x)}k,l is the estimated value of local ISR, and a mean of a prior probability model of the {circumflex over (x)}k,l is the {circumflex over (x)}k.
-
19.发明授权公开(公告)号：US11178340B2
公开(公告)日：2021-11-16
申请号：US16904586
申请日：2020-06-18
发明人： Narumi Sato , Ryohei Kagawa
摘要： A control device includes: a hardware processor; and a memory, wherein the hardware processor is configured to: control an image sensor configured to generate an image signal by performing imaging sequentially according to predetermined frames; detect a frequency of vocal cord vibration of a subject based on a voice signal; set a pulse width and a light emission cycle for when a light source emits light, based on the frequency and a preset duty cycle; control the light source to emit the pulse light using the pulse width and the light emission cycle in one field period or one frame period of the image sensor in synchronization with the frequency; calculate, based on the light emission cycle or the frequency, a gain amount by which the image signal is to be multiplied; and multiply the image signal by the gain amount.
-
公开(公告)号：US11169765B2
公开(公告)日：2021-11-09
申请号：US16566805
申请日：2019-09-10
申请人： SUPER HI FI, LLC
IPC分类号： G06F3/16 , G11B27/036 , G11B27/28 , G10L25/48 , G05B15/02
摘要： Embodiments of the invention provide an audio blending system with a computing device that processes operations including receiving a transition request from a user including an out element and/or an in element of at least one transition between at least one content item of at least one recipe. The recipe includes a sequence of a plurality of elements of content of a break, where at least one content item includes audio content and/or video content. The operations include causing a track server to couple to a metadata file of the audio file using a wired or wireless link. The metadata file includes audio content parameters measured or calculated from the audio file. The operations include calculating a transition between the out element and the in element, selecting, assembling and scheduling the sequence of plurality of elements for the transition, and adding the out element to the at least one recipe.
-
-
-
-
-
-
-
-
-
搜索结果
996 条记录 (耗时 0.026 秒)
