Yamaha Vocaloid robot singer (with robot piano)
20100228 at 17:39 The embedded video shows a robot powered by the Vocaloid “voice synthesis” software. The movements and expressions were pre-programmed, but the generation of the singing voice from lyrics and score can be done in real-time apparently.
The piano is a Yamaha Disklavier of course, being controlled by the same program that is controlling the Vocaloid robot. This is a good example of state-of-the-art synthesis technology, and sounds natural and human to my ears.
The inputs for Vocaloid are:
- phonemes (lyrics)
- vocal line (music)
- expression (stresses, vibrato, etc.)
The inputs for Disklavier are:
- precise key presses
- precise pedal controls
Other inputs for the robot shown in the video are for mouth, face and head movements.
Wikipedia: Vocaloid (Crypton Future Media)
The Character Vocal Series is a computer music program that synthesizes singing in Japanese. Developed by Crypton Future Media, it utilizes Yamaha’s Vocaloid 2 technology with specially recorded vocals of voice actors. To create a song, the user must input the melody and lyrics. A piano roll type interface is used to input the melody and the lyrics can be entered on each note. The software can change the stress of the pronunciations, add effects such as vibrato, or change the dynamics and tone of the voice.
The series is intended for professional musicians as well as light computer music users. The programmed vocals are designed to sound like an idol singer from the future. According to Crypton, because professional singers refused to provide singing data, in fear that the software might create their singing voice’s clones, Crypton changed their focus from imitating certain singers to creating characteristic vocals. This change of focus led to sampling vocals of voice actors.[11]
Each Japanese Vocaloid is given an anime-type character with specifications on age, height, weight, and musical strengths (genre, pitch range and ideal tempos). The characters of the first three installments of the series are created by illustrator Kei.
Any rights or obligations arising from the vocals created by the software belong to the software user. Just like any music synthesizer, the software is treated as a musical instrument and the vocals as sound. Under the term of license, the Character Vocal Series software can be used to create vocals for commercial or non-commercial use as long as the vocals do not offend public policy. In other words, the user is bound under the term of license with Crypton not to synthesize derogatory or disturbing lyrics. On the other hand, copyrights to the mascot image and name belong to Crypton. Under the term of license, a user cannot commercially distribute a vocal as a song sung by the character, nor use the mascot image on commercial products, without Crypton’s consent.
It is encouraging to read that “professional singers refused to provide singing data” because, as you were warned in The Performing Pianist (a pocket primer, 2002), page 27 (Digital vs. Analog):
Pianists are for the most part analog creatures. They may be transformed into digital entities by such things as the glorified player piano, the Yamaha Disklavier. This hybrid machine digitally and precisely captures the manipulations of the keys and pedals, also known as performance capture, which can then be reproduced exactly, ad infinitum, on the analog piano. A lazy individual could purchase and not play this instrument, thus avoiding the need to hire (or bribe) musicians, take lessons, or even go to concerts. This is not in the best interests of the art form. You should consider carefully the degree to which you agree to be digitized…
RELATED: Fauxharmonic Orchestra - The Robot Philharmonic
review,
video | tagged
live performance,
music,
review,
robot,
simulation,
video,
voice 



