diff --git a/_pages/demos/emotional-tts.md b/_pages/demos/emotional-tts.md index 74910821..160bfd7f 100644 --- a/_pages/demos/emotional-tts.md +++ b/_pages/demos/emotional-tts.md @@ -5,6 +5,8 @@ permalink: "/explore/emotional-tts/" fancy_audio_player: True --- +*This is a work from 2021* + Using our rich Emotional TTS system, we deliver the right tonality and superior customer experience in our dialog systems. This page showcases a sample of emotional presets and variations from our synthesizer. diff --git a/_pages/demos/natural-tts.md b/_pages/demos/natural-tts.md index 7100a955..40d29671 100644 --- a/_pages/demos/natural-tts.md +++ b/_pages/demos/natural-tts.md @@ -5,6 +5,8 @@ permalink: "/explore/natural-tts/" fancy_audio_player: True --- +*This is a work from 2021* + Our TTS has the state of the art results in Naturalness. Below, we present some example audio's generated by our TTS as contrasted against Google-TTS.
diff --git a/_pages/demos/speaker-entrainment.md b/_pages/demos/speaker-entrainment.md index 60383915..0f23890b 100644 --- a/_pages/demos/speaker-entrainment.md +++ b/_pages/demos/speaker-entrainment.md @@ -5,6 +5,8 @@ permalink: "/explore/speaker-entrainment/" fancy_audio_player: True --- +*This is a work from 2021* + Speaker entrainment is a phenomenon observed in human-human conversations where one interlocutor attunes their speech's acoustic, lexical and semantic features to the other interlocutor. This project aims to create a bot which can entrain on the acoustic features of user's speech. Incorporating such behavior into bots is known to increase trust, naturalness and likeability, which is likely to increase customer satisfaction and call resolution rate. diff --git a/_pages/demos/voice-cloning.md b/_pages/demos/voice-cloning.md index db76f80d..a2bc4fad 100644 --- a/_pages/demos/voice-cloning.md +++ b/_pages/demos/voice-cloning.md @@ -5,6 +5,8 @@ permalink: "/explore/voice-cloning/" fancy_audio_player: True --- +*This is a work from 2021* + Presenting some results of the Beta Feature of Voice Cloning that we currently support in our TTS. We trained our model on 30 mins of recordings from a new speaker. Some examples of both the target and generated audio are added below.