Integration of third party virtual assistants
A speech-enabled dialog system responds to a plurality of wake-up phrases. Based on which wake-up phrase is detected, the system's configuration is modified accordingly. Various configurable aspects of the system include selection and morphine of a text-to-speech voice; configuration of acoustic model, language model, vocabulary, and grammar; configuration of a graphic animation; configuration of virtual assistant personality parameters; invocation of a particular user profile; invocation of an authentication function; and configuration of an open sound. Configuration depends on a target market segment. Configuration also depends on the state of the dialog system, such as whether a previous utterance was an information query.
1. A method of providing access to a third party virtual assistant, the method comprising:
receiving, from a device, speech audio and an indication of which of a plurality of wake-up phrases the device detected;
sending, in response to the indication that indicates a particular wake-up phrase, the speech audio to the third party virtual assistant, wherein the third party virtual assistant provides a third party knowledge domain; and
receiving a response from the third party virtual assistant.
2. The method of claim 1 wherein the response is voice audio including a distinctive voice, the method further comprising sending the voice audio to the device.
3. The method of claim 1 wherein the response is text, the method further comprising:
synthesizing voice audio corresponding to the text using a text-to-speech voice corresponding to the indication indicating the particular wake-up phrase; and
sending the voice audio to the device.
4. A method of providing access to a virtual assistant, the method comprising:
receiving, from a device, speech audio and an indication of which of a plurality of wake-up phrases the device detected;
sending, in response to the indication indicating a particular wake-up phrase, the speech audio to the virtual assistant, wherein the virtual assistant provides at least one knowledge domain; and
performing automatic speech recognition on the speech audio to recognize text.
5. The method of claim 4 further comprising receiving a response from the virtual assistant wherein the response is voice audio having a distinctive voice, the method further comprising sending the voice audio to the device.
6. The method of claim 5 wherein the device is shared and the distinctive voice is gender-appropriate for a registration choice by a user.
7. The method of claim 4 further comprising:
receiving a text response from the virtual assistant;
synthesizing voice audio corresponding to the text response using a text-to-speech voice corresponding to the indication indicating the particular wake-up phrase; and
sending the voice audio to the device.
8. The method of claim 7 further comprising:
receiving a 3D graphic animation having a mouth; and
coordinating movement of the mouth with the synthesized voice audio; and
sending the animation to the device.
9. The method of claim 7 , wherein the synthesizing of the voice audio comprises performing speech morphing by assigning values to parameters that affect fundamental frequency and spectral characteristics.
10. The method of claim 7 wherein the device is shared and the text-to-speech voice is gender-appropriate for a registration choice by a user.
11. The method of claim 4 further comprising:
causing a function on a second device to capture sound;
emitting a tone;
receiving, by the second device, the emitted tone; and
authenticating the second device in response to the second device receiving the emitted tone.
12. The method of claim 4 , wherein the particular wake-up phrase is recognized only under a certain condition.
13. The method of claim 4 further comprising:
receiving location information; and
enabling a plugin based on the location information.
14. The method of claim 4 further comprising enabling a plugin based on a time of day.