Classifications

• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L15/00—Speech recognition
  • G10L15/28—Constructional details of speech recognition systems
  • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L17/00—Speaker identification or verification techniques
  • G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Definitions

• the present invention relates to a method and apparatus for identifying sounds. Though the principal intention is to identify particularly birds on the basis of their calls, there is nothing to prevent the invention from being used to identify other sounds too.
• Birdcalls in their various forms for example, calls marking territories, calls searching for a mate, and other typical calls have been recorded in natural conditions and collected, for example, on commercial CD records.
• the idea is that when a birdwatcher hears an unknown birdcall, it will be possible to listen to the CD, to identify the call heard as being that of a specific bird.
• the present invention is intended to create a method and apparatus, by means of which the sounds of birds and possibly also other animals can be identified with a great degree of certainty, as quickly as possible, while also bringing the advantage that one interested in birds no longer needs to rely on fading memories of the nature and type of sounds.
• Figure 1 shows one embodiment of the invention as a schematic diagram
• Figure 2 shows another embodiment of the invention, also as a schematic diagram.
• the device according to Figure 1 comprises a device 2 for capturing sounds.
• This device is usually a directional microphone, which can be moved to search for the birdcall, or similar sound it is wished to monitor. This sound is then listened to using earphones 5, or any other suitable device and, once an apparently suitable sound of suitable quality is heard, it can be forwarded, using a cable 4 or similar and a device 6, to the apparatus 3, in which it is recorded and in which it can be further processed.
• the microphone apparatus or device 6 can also include a memory, which permits a sound sample to be recorded and to be sent at a later stage. It is then possible to exploit the fact that only once a completely satisfactory sound sample has been obtained is it sent for comparison.
• the data is sent with the aid of the device 6 to be processed elsewhere, in which case a powerful apparatus 3 located in suitable premises receives the data and carries out the analysis and returns the result of the analysis using the aforesaid transmission/reception channel.
• the apparatus 3 is naturally a computer-type apparatus and particularly a computer with a large processing capacity, in the memory of which samples of all the birdcalls that may be required are recorded.
• the device 6 could be, for example, a portable computer, which includes a suitable component for wireless data transfer.
• a cheaper device 6, which is available to every user is a mobile telephone, which has suitable properties for transmitting sound data wirelessly.
• the sound captured and recorded in the apparatus 3 is now compared with the sound samples of the sound archive and the result of the comparison is shown on a display device, either the display of a microcomputer or the display of a telephone.
• Figure 2 shows an alternative, in which, in place of the microcomputer 6 shown in Figure 1 , a mobile telephone is used to send and receive the data.
• the data can be send and received using any known protocol.
• the embodiments of Figures 1 and 2 do not differ from each other, because the sending and reception of data to and from the computer 6 will most probably take place using mobile telephone technology.
• the microphone 2 is connected using a suitable adapter to the mobile telephone 6, from which a connection is opened to the apparatus 3 containing the sound archive.
• the sound sample is sent to the apparatus 3, which analyses the sample and returns the identification data to the mobile telephone, either during the same connection, or, for instance, as a text message, once identification has been carried out.
• a suitable price is calculated for the aforesaid services, which is charged, for example, directly in the mobile telephone bill.
• the reception of image data is also entirely possible and indeed sensible.
• the server 3 not only sends information as to what bird is in question, but also sends one or several pictures of the said songster.
• it is also possible to send other information concerning the bird such as information on its living environment, habits and distribution, etc.
• it is also possible to send an image to a mobile telephone though the displays of present mobile telephones generally do not provide a sufficiently clear image to permit the identification of a bird.
• the system according to the invention can, as such, be used not only for direct identification, but also as an archive, from which it is possible to retrieve, for example, a sound sample of a bird and possibly a picture, without having to enter a sound sample in it. In that case, only a simple query according to a certain protocol need be made.

Landscapes

• Engineering & Computer Science (AREA)
• Health & Medical Sciences (AREA)
• Audiology, Speech & Language Pathology (AREA)
• Human Computer Interaction (AREA)
• Physics & Mathematics (AREA)
• Acoustics & Sound (AREA)
• Multimedia (AREA)
• Computational Linguistics (AREA)
• Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
• Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Priority Applications (1)

Applications Claiming Priority (2)

Publications (2)

Family

ID=8560854

Family Applications (1)

Country Status (3)

Cited By (4)

Citations (5)

• 2001
  • 2001-03-27 FI FI20010632A patent/FI20010632A/fi unknown
• 2002
  • 2002-03-21 AU AU2002242763A patent/AU2002242763A1/en not_active Abandoned
  • 2002-03-21 WO PCT/FI2002/000239 patent/WO2002077898A2/en not_active Application Discontinuation

Patent Citations (5)

Non-Patent Citations (3)

Also Published As

Similar Documents

Legal Events