76 results about "Acoustic voice analysis" patented technology

A personal alerting device and method for detecting an approaching sound source includes a sound detector for detecting environmental sounds and for providing an electrical signal to a sound analyzer. The sound signal is analyzed to determine a baseline sound pattern comprising a plurality of distinct sounds corresponding to sounds emitted from a reference sound source. The distinct sounds in the baseline sound pattern may have substantially the same amplitude and time interval. The sound signal is monitored and compared against the baseline sound pattern to determine whether a target sound pattern is present in the sound signal, the target sound pattern corresponding to sounds emitted by the approaching sound source. When it is determined that the target sound is present in the sound signal, one or more of an audible, visual and tactile alert may be emitted to provide warning of the approaching sound source.

Systems for and methods of assessing urinary flow rate via sound analysis. Embodiments of the uroflow measurement systems include a computer and a telephone or a digital recording mechanism to capture the sound of one or more urination events, which are stored as audio files in a database The uroflow measurement systems may include sound analysis software for analyzing the strength and duration of each urination event and may include a web-based uroflow software application for viewing the results via the Internet or other network In one embodiment, the sound analysis software performs the steps of reading in the raw data of a selected audio file, generating a plot of the audio signal amplitude vs. time, generating a plot of smoothed data for the purpose of presenting an outline of the flow, generating a main flow plot, which is a plot of the largest continuous flow that has a strength that is greater than a predetermined minimum, and generating a set of numerical values that correspond to the strength and duration of urination.

The present invention provides a voice recognition apparatus and a voice recognition method. An extraction unit respectively extractes feature amounts from a plurality of voice data relative to a plurality of rejected words when the rejected words are applied to recognition words registered in the word dictionary. A collation unit calculates a degree of similarity between the voice signal and each of the recognition words and reject words stored in the word dictionary by using the feature amount extracted by the extraction unit. A result determination unit determines whether or not a word having a high calculated degree of similarity corresponds to a reject word, when the word is determined as the reject word. A reject word generation unit generates an acoustic model from a voice signal having a high degree of similarity to the recognition word to which the reject word is added, calculated by the collation unit, and stores the generated acoustic model in the word dictionary as a reject word relating to the recognition word.

A prosody identifying apparatus for identifying input speech on the basis of prosodic features of the input speech is provided. The prosody identifying apparatus includes a sound analyzing section for acquiring an amount of change in movement of a feature distribution obtained from an autocorrelation matrix of the frequency characteristic of the input speech and an identifying section for recognizing the input speech on the basis of an output of the sound analyzing section.

An apparatus for analyzing music based on sound information of instruments is provided. The apparatus uses sound information of instruments or the sound information and score information in order to analyze digital sounds. The sound information of instruments performed to generate digital sounds is previously stored by pitches and strengths so that monophonic notes and polyphonic notes performed by the instruments can be easily analyzed. In addition, by using the sound information of instruments and score information together, input digital sounds can be accurately analyzed and can be detected in the form of quantitative data.

The invention relates to a monitoring and alarming device for the working state of an anvil of a diamond cubic press. The monitoring and alarming device comprises a host and a monitoring and alarming system. The monitoring and alarming system comprises an image collection module, a sound collection module, an image analysis module, a sound analysis module and an I/O communication module. The first output end and the first input end of the I/O communication module are connected with the input end and the output end of a control cabinet of the cubic press respectively, and the second output end and the third output end of the I/O communication module are connected with the input end of the image collection module and the input end of the sound collection module respectively. The output end of the image collection module and the output end of the sound collection module are connected with the input end of the image analysis module and the input end of the sound analysis module respectively, and the output end of the image analysis module and the output end of the sound analysis module are connected with the second input end of the I/O communication module. By means of the monitoring and alarming device, the anvil cracking judging accuracy is improved, and the accurate anvil cracking position is visibly displayed; an operator can master the working state of the cubic press in real time, and thus loss caused by anvil cracking is reduced.

The embodiment of the invention discloses a voice enhancement method and device, relates to the technical field of communication, and solves the problems that in the prior art, in a scene with a complex sound environment, the environment cannot be self-adapted, and the experience of user intelligent interaction is poor. According to the invention, by adopting the artificial intelligence technology, the intelligent interaction experience of users can be improved. The method comprises steps: electronic equipment collects a first sound, wherein the first sound comprises at least one of a second sound and a background sound; the electronic equipment identifies the first sound; when the second sound exists in the first sound, the electronic equipment performs sound analysis on the second soundto obtain a third sound; and the electronic equipment processes the third sound.

The invention provides a speech recognizer, a speech recognition method and a speech recognition program. The speech recognizer (1) comprises a speech collating section (17) for calculating similarities at each time between the amount of a feature converted by a speech analysis section (11) and word models generated by a word model generating section (16). The speech collating section (17) extracts the word model in which the minimum similarity in the similarities at each time or the entire similarity obtained from the similarities at each time out of the word models generated by the word model generating section (16) satisfies a second threshold condition, and in which similarities at each time in the section corresponding to the phoneme or the phoneme string associated with the first threshold condition out of the speech sections of utterance speech satisfy the first threshold condition and outputs the recognized word corresponding to the extracted word model as the result of the recognition.

In one embodiment, a pause-based music detection (MD) module detects music by analyzing pauses in a received audio signal. The energy of each frame of the signal is compared to an energy threshold to determine whether the frame corresponds to background noise only (i.e., a pause) or sound such as speech or music. A window having a number of frames is analyzed to determine whether there is a pause within the window. If no pauses are detected in the window, then the current frame is presumed to correspond to music. If a pause is detected, then the current frame is presumed to correspond to speech. In another embodiment, the pause-based MD module output is applied to Boolean “OR” logic along with a tone-based MD module output to generate a final MD decision. The tone-based MD module detects music by analyzing tones in the signal using any suitable tone-based MD algorithm.

A music listening and singing teaching system comprises a sound collecting unit for collecting a singing voice of a user, a sound analyzing unit electrically connected with the sound collecting unit and used for comparing the singing voice with a sample sound, an integrated processing unit electrically connected to the sound analyzing unit and used for generating a corrected audio according to thecomparison result, an audio correction unit electrically connected to the integrated processing unit and used for playing the corrected audio, and a sound playing unit electrically connected to the integrated processing unit and used for playing the singing voice or the sample sound. The music listening and singing teaching system enables the user to acquire the precise difference between the singing voice and the sample sound, so that the user can continuously his own level during the practice, and the teaching efficiency is higher.

The invention discloses a detection and alarming system for falling of an indoor worker. The system comprises a detection system and an alarming system, wherein the detection system comprises a thermal imaging module, a manual alarming button, a sound module and a time control module; the thermal imaging module comprises a support which can be rotated within an angle of 300 DEG; a thermal imaging instrument is installed on the support; the sound module comprises a sound analyzer and a noise shielding device; the time control module is in an electric-signal connection with the thermal imaging instrument and the sound analyzer separately; the alarming system comprises a cellular communication module and a controller; the controller is separately connected to the time control module and the manual alarming button; the cellular communication module comprises a receiving terminal and a GSM communication terminal which records relevant information of a user; the controller is connected to the GSM communication terminal; and the GSM communication terminal sends detection information to the receiving terminal by electric signals. The system disclosed by the invention can effectively prevent personal privacy leakage, and can also send out alarming and help calling in time aiming at different situations happening after the user falls; and rescue efficiency for rescue workers can also be increased by the relevant information recorded in the GSM communication terminal.

The invention provides an intelligent access control system for realizing door opening through voice recognition, and the intelligent access control system for realizing door opening through voice recognition comprises a sound sensing module which is used for detecting sound data of a current door opening user; a sound analysis module which is used for analyzing the sound data detected by the sound sensing module; and an access control module which is used for controlling opening and closing of the door according to the analysis result of the sound analysis module. According to the intelligentaccess control system for realizing door opening through voice recognition, a single sensing mode at present is changed, non-contact recognition is realized, the information safety can be better ensured, and the detection efficiency is improved; in addition, from the aspect of information collection, sound collection is more convenient, and meanwhile the uniqueness and privacy are better achieved; moreover, from the perspective of security and protection, the security and the controllability of information are realized.

The disclosure relates to a system for generating a status output based on sound emitted by an animal. The system comprising: a client (102), a server (104) and a database (106); the database (106) is accessible (107) by the server (104) and comprises historic sound data pertaining to the animal (302) or animals of the same type as the animal; the client (102) comprising circuitry (110) configured to: detect (202) sound emitted (308, 312) by the animal (302); record (204) the detected sound (308, 312); analyze (206) the recorded sound for detecting whether the sound (308, 312) comprises a specific sound characteristic out of a plurality of possible sound characteristics, wherein the sound characteristic includes at least one of intensity, frequency and duration of the detected sound; transmit (208), in response to detecting that the sound (308, 312) comprises the specific sound characteristic, the recorded sound to a server (104); the server (104) comprises circuitry (122) configured to: receive (210) the recorded sound; classify (212) the recorded sound by comparing one or more sound characteristics of the recorded sound with the historic sound data comprised in the database (106); generate (214) the status output based on the classification of the recorded sound. A method (200) for generating a status output based on sound emitted by an animal is also provided.