Browse Prior Art Database

Voice Activated Music System

IP.com Disclosure Number: IPCOM000105979D
Original Publication Date: 1993-Sep-01
Included in the Prior Art Database: 2005-Mar-20
Document File: 2 page(s) / 67K

Publishing Venue

IBM

Related People

Farrett, PW: AUTHOR [+2]

Abstract

Disclosed is an approach to a voice I/O system for music or multimedia applications in which musical parameters are automatically activated based on voice command input.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 52% of the total text.

Voice Activated Music System

      Disclosed is an approach to a voice I/O system for music or
multimedia applications in which musical parameters are automatically
activated based on voice command input.

      Current computer-based musical systems are based on user
interaction with MIDI I/O capability (e.g., musical keyboard, PC
keyboard, or music synthesizer module).  This process assumes that a
musician encodes all necessary musical performance information to be
interpreted and processed (i.e., the burden is placed on the
musician).  This process is slow since all detail of the musical
performance must be manually entered and cumbersome since a computer
pointing device (e.g., mouse) must be used.

      The approach taken in this disclosure assumes less burden for
the musician (or end user who is not a musician) since he no longer
inputs musical sequences by "hand"; rather, voice command input yield
computer-generated (automated) sequences, which "fill in" or modify
desired musical parameters such as pitch, chord sequence,
instrumentation, style, etc.

      A System environment for a voice activated system would consist
of the following.  Voice Input: A voice recognition based on
utterances discrete continuous (word or phrase) recognition based on
utterances (i.e., lexical).  Voice Output: A speech synthesizer
(text-to-speech), which outputs musical parameters generated (i.e.,
speech output of musical parameters and not the music generated).
Music Output: automated comuter generated music via MIDI.  Session:
Musician sits in front of system, inputs via voice the musical
elements desired; system outputs musical (generated) parameters and
synthesized speech (output).

      The following illustrates an example session (discrete or
continuous), which is in structured-English format.  For
discrete/continuous utterance (isolated or non-isolated words)  Do:

1.  Ma...