Performance evaluator for use in a karaoke apparatus

• US 5,557,056 A
• Filed: 09/22/1994
• Issued: 09/17/1996
• Est. Priority Date: 09/23/1993
• Status: Expired due to Fees

• Current Assignee: Daewoo Electronics (Government of South Korea)
• Original Assignee: Daewoo Electronics Company Limited (Dayou Holdings Co.,Ltd.)
• Inventors: Kim, Ul-Je, Hong, Jae-Gyoo
• Primary Examiner(s): Witkowski, Stanley J.
• Application Number:
  US08/310,442
• Time in Patent Office: 726 Days
• Field of Search: 84/601, 84/602, 84/609-614, 84/634-638, 84/477 R, 84/478
• US Class Current: 84/610
• CPC Class Codes: G09B 15/00 Teaching music metronomes G04F5/02
• CPC Class Codes: G10H 1/0008 Associated control or indicating means
• CPC Class Codes: G10H 1/361 Recording/reproducing of accompaniment for use with an external source, e.g. karaoke systems
• CPC Class Codes: G10H 2210/091 for performance evaluation, i.e. judging, grading or scoring the musical qualities or faithfulness of a performance, e.g. with respect to pitch, tempo or other timings of a reference performance

Abstract

A karaoke apparatus evaluates a singer'"'"'s performance by employing: a microphone for converting the singer'"'"'s voice into a electrical voice signal; a first analogue to digital (A/D) converter for converting the electrical voice signal into a digitized voice signal; a audiovisual equipment for producing the accompanying music; a second A/D converter for digitizing the accompanying music to produce a digitized accompaniment signal; and a performance evaluator for measuring the difference between the accompanying music and the corresponding karaoke singer'"'"'s voice to produce a score for the karaoke singer'"'"'s singing performance.

Claims

1. A karaoke apparatus capable of evaluating the singing performance of a karaoke singer by measuring the incongruity between an accompanying music and the karaoke singer'"'"'s rendition to the accompanying music, which comprises:

a microphone for converting the singer'"'"'s rendition into an electrical voice signal;

a first analog to digital converter (A/D) converter for converting the electrical voice signal into a digitized voice signal;

an audiovisual equipment for producing the accompanying music;

a second A/D converter for digitizing the accompanying music to produce a digitized accompaniment signal;

a performance evaluator for measuring the difference between an energy distribution of the digitized voice signal and that of the digitized accompaniment signal to thereby evaluate the karaoke singer'"'"'s singing performance, wherein said performance evaluator includes;

means for dividing the digitized voice signal and the digitized accompaniment signal into n groups, respectively, wherein each group contains a predetermined number of digitized subsignals, and calculating an energy for each of the n groups of the digitized voice and the accompaniment subsignals to produce n voice energies and n accompaniment energies, respectively;

means for summing the n voice energies and the n accompaniment energies to produce a voice energy sum and an accompaniment energy sum, respectively;

means for normalizing each of the n voice energies and each of the n accompaniment energies through the use of the voice energy sum and the accompaniment energy sum, respectively;

means for producing an error rate by measuring the difference between each of the normalized n voice energies and each of the normalized n accompaniment energies; and

means for calculating a score of the singer'"'"'s singing performance on a basis of the error rate.

2. The apparatus as recited in claim 1, wherein each of the voice and accompaniment energies is calculated as:

##EQU5##

space="preserve" listing-type="equation">w(k)=1, where 0≦

k≦

N-1=0, otherwise

wherein E(n) represents the voice or accompaniment energy for the nth group of the predetermined number of digitized subsignals, n ranging from 1 to D, D=M//N, M representing the total number of the digitized voice or accompaniment subsignals, N being the predetermined number of the digitized subsignals included in each of the n groups of the voice or the accompaniment signal, and the "//" notation symbolizes an integer division with rounding to a nearest integer;

x(m) is a digital value of the voice or the accompaniment subsignals in each group, with m=1, 2, . . . , M; and

w(k) is a window function, with k=0, 1, 2, . . . , N-1.

3. The apparatus of claim 2, wherein said error rate, Er, is calculated as:

##EQU6## wherein E1'"'"'(n) represents the nth group of the normalized voice energies and E2'"'"'(n) the nth group of the normalized accompaniment energies; and

n and D have the same meanings as previously defined.

4. The apparatus of claim 3, wherein said singing performance, S, is measured by the formula of:

space="preserve" listing-type="equation">S=60+40(1-Er)

5. The karaoke apparatus of claim 4, wherein said apparatus further comprises a display means for displaying the calculated score.