Uncanny valley. It results in all sorts of negative reactions in me when I deal with a near-human bot, more so than a normal mechanical one. Sent from my iPhone
On Dec 11, 2015, at 2:50 PM, Alex Balashov <abalashov at evaristesys.com> wrote:
Over the last half decade or so, there has been a big movement toward automatic speech recognition (ASR) coupled with text-to-speech (TTS) that has a much more "natural" tone and cadence.
"Huh! Sounds kind of like a real human, actually!" is all the rage, while robotic recordings are out.
There's a huge polarisation in ASR and TTS technologies. The bad ones - e.g. the stock add-ons in the open source world - are pretty bad. The good ones, however, are really, _really_ good. And really expensive.
Last I heard Voxeo is still the market leader in that second category, but things may have changed.
-- Alex Balashov | Principal | Evariste Systems LLC 303 Perimeter Center North, Suite 300 Atlanta, GA 30346 United States
Tel: +1-800-250-5920 (toll-free) / +1-678-954-0671 (direct) Web: http://www.evaristesys.com/, http://www.csrpswitch.com/ _______________________________________________ VoiceOps mailing list VoiceOps at voiceops.org https://puck.nether.net/mailman/listinfo/voiceops