초록 ▼

A customer for music distributed over the interne may select a composition from a menu of written identifiers (such as the song title and singer or group) and then confirm that the composition is indeed the one desired by listening to a corrupted version of the composition. If the customer has forgo

A customer for music distributed over the interne may select a composition from a menu of written identifiers (such as the song title and singer or group) and then confirm that the composition is indeed the one desired by listening to a corrupted version of the composition. If the customer has forgotten the song title or the singer or other words that provide the identifier, he or she may hum or otherwise vocalize a few bars of the desired composition, or pick the desired composition out on a simulated keyboard. A music-recognition system then locates candidates for the selected composition and displays identifiers for these candidates to the customer.

대표청구항 ▼

1. A method of recognizing a musical composition from a specimen of a musical composition that has been vocalized or picked out by a person, comprising the following computer-implemented steps: (a) generating a pattern from the specimen, step (a) including identifying a tone in the specimen and gene

1. A method of recognizing a musical composition from a specimen of a musical composition that has been vocalized or picked out by a person, comprising the following computer-implemented steps: (a) generating a pattern from the specimen, step (a) including identifying a tone in the specimen and generating a scale from the tone; and(b) comparing the pattern generated in step (a) with patterns in a pattern library; and(c) identifying at least one musical composition from the comparison conducted in step (b) wherein step (a) further includes identifying a sequence of notes in the specimen, the notes being members of the scale. 2. The method of claim 1, wherein the specimen is picked out by the person on a simulated musical instrument. 3. The method of claim 1, wherein step (a) further includes determining the duration of the notes. 4. The method of claim 3, wherein the step of determining the duration of the notes comprises identifying a tone in the specimen that is currently the strongest tone, and determining when the strongest tone changes. 5. The method of claim 1, wherein the step of identifying a tone comprises filtering the specimen into a plurality of frequency, components, and determining which frequency component has the strongest signal. 6. The method of claim 1, wherein at least one of the patterns in the pattern library is an incomplete pattern that corresponds to part but not all of a musical composition, and that musical composition is identified based on the incomplete pattern. 7. The method of claim 1, further comprising the step of generating at least some of the patterns in the pattern library from incomplete portions of the musical compositions themselves. 8. A method of recognizing a musical composition from a specimen of a musical composition that has been vocalized or picked out by a person, comprising the following computer-implemented steps: (a) generating a pattern from the specimen, step (a) including filtering the specimen into a plurality of frequency, components, determining which frequency component currently has the strongest signal, and ascertaining the number of half-tones between a current frequency component that currently has the strongest signal and the frequency component that had the strongest signal immediately before the current frequency component; and(b) comparing the pattern generated in step (a) with patterns in a pattern library; and(c) identifying at least one musical composition from the comparison conducted in step (b). 9. The method of claim 8, wherein at least one of the patterns in the pattern library is an incomplete pattern that corresponds to part but not all of a musical composition, and that musical composition is identified based on the incomplete pattern.