Sound recognition is a technology, which is based on both traditional
pattern recognition
Pattern recognition is the automated recognition of patterns and regularities in data. It has applications in statistical data analysis, signal processing, image analysis, information retrieval, bioinformatics, data compression, computer graphics ...
theories and audio signal analysis methods. Sound recognition technologies contain preliminary data processing,
feature extraction
In machine learning, pattern recognition, and image processing, feature extraction starts from an initial set of measured data and builds derived values (features) intended to be informative and non-redundant, facilitating the subsequent learning a ...
and classification algorithms. Sound recognition can classify feature vectors. Feature vectors are created as a result of preliminary data processing and
linear predictive coding
Linear predictive coding (LPC) is a method used mostly in audio signal processing and speech processing for representing the spectral envelope of a digital signal of speech in compressed form, using the information of a linear predictive mod ...
.
Sound recognition technologies are used for:
*
Music recognition
*
Speech recognition
Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the ...
* Automatic alarm detection and identification for surveillance, monitoring systems, based on the acoustic environment
* Assistance to disabled or elderly people affected in their hearing capabilities
*
Identifying species of animals such as fish and mammals, e.g. in
acoustical oceanography
Hydroacoustics is the study and application of sound in water. Hydroacoustics, using sonar technology, is most commonly used for monitoring of underwater physical and biological characteristics.
Hydroacoustics can be used to detect the depth ...
Security
In monitoring and security, an important contribution to alarm detection and alarm verification can be supplied, using sound recognition techniques. In particular, these methods could be helpful for intrusion detection in places like offices, stores, private homes or for the supervision of public premises exposed to person aggression. In all these cases, a recognition system can report about a danger or distress event. It could further identify sounds like glass break, doorbells, smoke detector alarms, red alerts, human screams, baby cries and others. Sometimes, the alarm is triggered by other detectors (e.g. temperature or video-based) and the sound recognizer would be associated with these other modalities, to verify the alarm, with the purpose of decreasing the global false alarm detection rate.
Assistance
Solutions based on a sound recognition technology can offer assistance to disabled and elderly people affected in hearing capabilities, helping them to keep or recover some independence in their daily occupations.
Companies
There are only a handful of companies who are working on sound recognition technology:
*
AbiliSense (Generic sound recognition technology for a wide variety of use cases, mainly safety and security, and functional in environments such as: home and city).
*
Audio Analytic (AI company whose "Embedded sound recognition AI software gives consumer technology, such as smart speakers, hearables, smart home tech, mobile phones and automotive, a sense of hearing." has sound recognition software that makes consumer products more intelligent).
*
OtoSense (checking sounds of engines).
*
Wavio (software and product innovation company providing sound recognition solutions to clients such as product manufacturers, organizations, and government inclusive of accessibility for Deaf & hard of hearing, protected by sound recognition patents
[{{Cite patent, title=Apparatus and method for wireless sound recognition to notify users of detected sounds, pubdate=2018-08-28, country=US, number=10062304, assign=Hz Innovations Inc., inventor1-last=Watkins, inventor1-first=Greyson Kendall, inventor2-last=Baltzer, inventor2-first=Zachary, inventor3-last=Lamb, inventor3-first=Nicholas] covering sound recognition to notify users of detected sounds automatically).
See also
*
Acoustic fingerprint
An acoustic fingerprint is a condensed digital summary, a fingerprint, deterministically generated from an audio signal, that can be used to identify an audio sample or quickly locate similar items in an audio database.
Practical uses of aco ...
*
Shazam (application)
Shazam is an application that can identify music, movies, advertising, and television shows, based on a short sample played and using the microphone on the device. It was created by London-based Shazam Entertainment, and has been owned by Ap ...
References
Audio engineering
Security technology
Pattern recognition