Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
1998-09-01
2001-01-30
Zele, Krista (Department: 2748)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S207000
Reexamination Certificate
active
06182044
ABSTRACT:
BACKGROUND
1. Technical Field
The present application relates generally to system and methods for automatic vocal coaching and, more particularly, to system and methods for automatically critiquing the pitch, rhythm and pronunciation or diction of a vocal performance of a singer in accordance with pre-programmed criteria.
2. Description of the Related Art
It is often useful for a person who aspires to be a singer to have his/her vocal performance critiqued by a professional singing coach on a regular basis so that the person's singing skills can be sharpened. For instance, critiquing a person's pitch, rhythm, and diction during a vocal performance can help the person identify and focus on any weaknesses or shortcomings of his/her singing technique or style, which helps improve the person's singing ability. Unfortunately, few singers have a professional singing coach available on a continuous basis, and may unknowingly lapse into errors during their private practice sessions.
There are some commercially available interactive multimedia software programs which allow a person to practice his/her singing skills at his/her own pace and convenience. These multimedia programs, however, are limited and do not provide the level of guidance and assistance that a professional singing coach can provide. For instance, the multimedia program SING! by Musicware Inc. is one example of such software. The SING! program is very limited since it only deals with pitch and rhythm and cannot analyze songs. In particular, the user is provided with a series of vocal exercises in a certain sequence that the user must perform and the program checks the exercises. Accordingly, there is a need for an interactive multimedia vocal coaching system that can provide the level or breadth of guidance that a singer can receive from a professional vocal coach.
SUMMARY
The present application is directed to system and methods for providing vocal coaching by automatically critiquing pitch, rhythm and pronunciation or diction of a vocal performance of a singer in accordance with pre-programmed criteria.
In one aspect, a system for analyzing a vocal performance, comprises:
means for receiving input utterances corresponding to a current vocal performance;
means for extracting pitch information from the input utterances of the current vocal performance;
means for extracting phonetic information from the input utterances of the vocal performance;
means for combining and encoding the pitch and phonetic information into an encoded representation of the vocal performance; and
means for outputting the encoded representation.
In another aspect, a method for analyzing a vocal performance, comprises the steps of:
providing acoustic utterances corresponding to a current vocal performance; extracting pitch information from the acoustic utterances;
extracting phonetic information from the acoustic utterances;
combining the extracted pitch and phonetic information into an encoded representation of the current vocal performance;
comparing the encoded representation of the current vocal performance with a corresponding encoded reference performance having pitch and phonetic information associated therewith; and
providing a critique if one of the pitch information and the phonetic information of the encoded current vocal performance varies from the corresponding pitch and phonetic information of the encoded reference performance.
These and other objects, features and advantages of the present system and methods will become apparent from the following detailed description of illustrative embodiments, which is to be read in connection with the accompanying drawings.
REFERENCES:
patent: 5548647 (1996-08-01), Naik et al.
patent: 5651095 (1997-07-01), Ogden
patent: 5659664 (1997-08-01), Kaja
patent: 5727120 (1998-03-01), Van Coile et al.
patent: 5728960 (1998-03-01), Sitrick
patent: 5857171 (1999-01-01), Kageyama et al.
patent: 5905972 (1999-05-01), Huang et al.
patent: 5913194 (1999-06-01), Karaali et al.
Yoshida et al, “A New Method of Generating Speech Synthesis Units . . . ”, ICLSP 1996.
Masuko et al, “Voice Characteristics Conversion of HMM Based Speech synthesis System”, ICASSP 1997.
Saito et al, High Quality Speech Synthesis using Context Dependent Syllabic Units, ICASSP, 1996.
Fong Philip W.
Strother Nelson B.
F. Chau & Associates LLP
International Business Machines - Corporation
Opsasnick Michael N.
Zele Krista
LandOfFree
System and methods for analyzing and critiquing a vocal... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and methods for analyzing and critiquing a vocal..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and methods for analyzing and critiquing a vocal... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2502070