Method and a system for recognizing a melody
AssigneeNokia Mobile Phones Ltd.
InventorsJyri Huopaniemi, Timo Sorsa, Peter Boda
Life of this patent
Estimating the term…
Abstract
The invention relates to a method for recognizing a melody from a set of stored melodies. In the method, an audio sample representing the melody to be recognized is produced to form a first search criterion. In the method, an audio sample is produced of at least one word related to the melody to be recognized to form a second search criterion, wherein in the recognition, a first search set is formed of the stored melodies on the basis of one said search criterion. Another said search criterion is used for recognizing the melody from said first search set.
Claims18
A method for recongnizing a melody from a set of stored melodies, the method comprising:
- producing an audio sample including first parts having speech and second parts having a melody, the first and second parts located at different time instants in the audio sample;
- detecting speech from the audio sample to separate from the audio sample the first parts and the second parts;
- on the basis of the separation, forming a first search critrtion from the second parts by producing an audio sample representing a melody to by recognized;
- on the basis of the separation, forming a second search criterion by producing an audio sample including at least one word from the first parts;
- forming a first search set of the stored melodies on the basis of one of the search criterion;
- and
- using another of the search criterion for recognizing the melody from the first search set.
A system comprising:
- means (7) for storing melodies;
- means (3, 3a) for producing an audio sample including speech and a melody to be recognized;
- a speech recognizer for separating the audio sample into parts having speech and parts without speech;
- means (5) for forming a first search criterion on the basis of the parts without speech;
- means (4) for forming a second search criterion on the basis of the parts having speech;
- means (6a) for forming a first search set of the stored melodies on the basis of one of the search criterion;
- and
- means for recognizing the melody from said first search set on the basis of another of the search criterion.
A database server (1) comprising:
- means (7) for storing melodies;
- means (8) for receiving an audio sample including speech and a melody to be recognized;
- a speech recognizer for separating the audio sample into parts having speech and part without speech;
- melody recognition means (5) for forming a first search criterion on the basis of the parts without speech;
- means (4) for forming a second search criterion from at least one word in the parts having speech related to the melody to be recognized;
- means (6a) for forming a first search set of the stored melodies on the basis of one of the search criterion;
- and
- means (6b) for recognizing the melody from said first search set on the basis of another of the search criterion.
Dependencies are inferred from the claim text.