Date: 3/10/2018 17:33:19
From: dv
ID: 1283925
Subject: Early speech synthesis

One of the early attempts to partially replicate human speech was the set of vowel horns made by Christian Kratzenstein in 1780. These mimicked the five basic vowel sounds without any attempt at replicating consonants.

About a decade after that, Wolfgang von Kempelen completed work on his speech engine. The final version consisted of a bellows, reed, a mock-up of the human oral and nasal cavities, a rubber mouth worked by hand, and a string-operated flap representing the tongue. This gave a fair approximation of several consonants.

Here is a video of a replica of Kempelen’s machine being operated

In 1938, Bell Labs developed a vocoder for compressing and simplifying recorded human speech. As a “proof of concept” project, they also developed a hand operated “Voder”, which could generate human speech. There were two sources of sound: a buzzing tube, for vowels, nasals and voiced consonants, and a hissing tube for voiceless consonants. These signals were passed through any of various bandpass filters.

Here is a video of the Voder in operation

Reply Quote

Date: 3/10/2018 17:40:09
From: Bubblecar
ID: 1283927
Subject: re: Early speech synthesis

Interesting, ta. Had to turn the Kempelen one right down to avoid scaring the neighbours. The Voder was impressive, seemingly better quality than Stephen Hawking’s voice.

Reply Quote

Date: 3/10/2018 17:48:43
From: Cymek
ID: 1283932
Subject: re: Early speech synthesis

Welcome to Big Mouth for the Commodore 64 was one I remember

Reply Quote

Date: 3/10/2018 17:52:06
From: dv
ID: 1283934
Subject: re: Early speech synthesis

https://youtu.be/TsdOej_nC1M
A longer Voder recording

Reply Quote

Date: 3/10/2018 18:02:30
From: Bubblecar
ID: 1283936
Subject: re: Early speech synthesis

dv said:


https://youtu.be/TsdOej_nC1M
A longer Voder recording

Well maybe not quite as good as Hawking’s voice.

And certainly much more difficult to operate by the sound of it.

Reply Quote

Date: 3/10/2018 18:16:11
From: dv
ID: 1283937
Subject: re: Early speech synthesis

Bubblecar said:


dv said:

https://youtu.be/TsdOej_nC1M
A longer Voder recording

Well maybe not quite as good as Hawking’s voice.

And certainly much more difficult to operate by the sound of it.

Mmm. In fairness to SJH, he can only make slight movements with one hand, whereas the Voder was a 10 key and foot-pedal job.

Reply Quote

Date: 3/10/2018 18:42:49
From: The Rev Dodgson
ID: 1283951
Subject: re: Early speech synthesis

dv said:


Bubblecar said:

dv said:

https://youtu.be/TsdOej_nC1M
A longer Voder recording

Well maybe not quite as good as Hawking’s voice.

And certainly much more difficult to operate by the sound of it.

Mmm. In fairness to SJH, he can only make slight movements with one hand, whereas the Voder was a 10 key and foot-pedal job.

Even slight movements with one hand are a pretty remarkable achievement for someone in his current condition.

Reply Quote

Date: 3/10/2018 18:53:46
From: Michael V
ID: 1283957
Subject: re: Early speech synthesis

The Rev Dodgson said:


dv said:

Bubblecar said:

Well maybe not quite as good as Hawking’s voice.

And certainly much more difficult to operate by the sound of it.

Mmm. In fairness to SJH, he can only make slight movements with one hand, whereas the Voder was a 10 key and foot-pedal job.

Even slight movements with one hand are a pretty remarkable achievement for someone in his current condition.

Ha!

Reply Quote

Date: 4/10/2018 01:01:03
From: SCIENCE
ID: 1284088
Subject: re: Early speech synthesis

how slight, i don’t think ‘e’s reached thermodynamic zero yet

Reply Quote

Date: 9/10/2018 03:53:10
From: Kothos
ID: 1286348
Subject: re: Early speech synthesis

Bubblecar said:


Interesting, ta. Had to turn the Kempelen one right down to avoid scaring the neighbours. The Voder was impressive, seemingly better quality than Stephen Hawking’s voice.

There are plenty of digitally synthesised voices much better than Hawking’s these days, but Hawking himself refused all offers to upgrade as he was attached to his voice and didn’t want any other.

Reply Quote

Date: 9/10/2018 03:53:11
From: Kothos
ID: 1286349
Subject: re: Early speech synthesis

Bubblecar said:


Interesting, ta. Had to turn the Kempelen one right down to avoid scaring the neighbours. The Voder was impressive, seemingly better quality than Stephen Hawking’s voice.

There are plenty of digitally synthesised voices much better than Hawking’s these days, but Hawking himself refused all offers to upgrade as he was attached to his voice and didn’t want any other.

Reply Quote