18539604. VOICE DIALOGUE SYSTEM AND METHOD OF UNDERSTANDING UTTERANCE INTENTION simplified abstract (TOYOTA JIDOSHA KABUSHIKI KAISHA)

VOICE DIALOGUE SYSTEM AND METHOD OF UNDERSTANDING UTTERANCE INTENTION

Organization Name

TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor(s)

Atsushi Ikeno of Kyoto-shi (JP)

Yusuke Jinguji of Hiroo-gun (JP)

Toshifumi Nishijima of Kasugai-shi (JP)

Fuminori Kataoka of Nisshin-shi (JP)

Horomi Tonegawa of Okazaki-shi (JP)

Norihide Umeyama of Nisshin-shi (JP)

VOICE DIALOGUE SYSTEM AND METHOD OF UNDERSTANDING UTTERANCE INTENTION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18539604 titled 'VOICE DIALOGUE SYSTEM AND METHOD OF UNDERSTANDING UTTERANCE INTENTION

Simplified Explanation

The abstract describes a voice dialogue system that includes a voice input unit, a dialogue text creator, a voice output unit, and a setting unit. The system is designed to output a second system utterance without acquiring a user utterance after the first system utterance, with the setting unit determining the timing for the output of the second system utterance.

• Voice dialogue system components:

   - Voice input unit: acquires user utterance
   - Dialogue text creator: creates system utterance text
   - Voice output unit: outputs system utterance as voice data
   - Setting unit: sets response deadline for system utterances

• Second system utterance structure:

   - Connective portion: connects following sentences
   - Content portion: subject of the second system utterance
   - Setting unit determines timing for output of connective or content portion as response deadline for first system utterance

Potential Applications

This technology can be applied in: - Customer service chatbots - Virtual assistants - Interactive voice response systems

Problems Solved

- Improving user experience in voice interactions - Streamlining dialogue flow in automated systems

Benefits

- Enhanced efficiency in voice dialogue systems - Seamless transition between system utterances - Increased user engagement

Potential Commercial Applications

Optimizing Voice Dialogue Systems for Enhanced User Experience

Possible Prior Art

No prior art information available.

Unanswered Questions

How does this technology handle interruptions during dialogue?

The abstract does not specify how the system deals with interruptions from the user or external factors.

What languages or accents is this technology optimized for?

The abstract does not mention the languages or accents for which the voice dialogue system is designed.

Original Abstract Submitted

A voice dialogue system includes: a voice input unit which acquires a user utterance, a dialogue text creator which creates a text of a system utterance, a voice output unit which outputs the system utterance as voice data, and a setting unit that sets a response deadline for system utterances. When a first system utterance is output by the voice output unit, a second system utterance is output after the first system utterance without having acquired a user utterance, and the second system utterance comprises a connective portion for connecting following sentences and a content portion that is a subject of the second system utterance, the setting unit sets a timing at which output of the connective portion of the second system utterance ends or output of the content portion of the second system utterance starts as the response deadline for the first system utterance.