Automatic interpretation server and method thereof
AssigneeElectronics and Telecommunications Research Institute
InventorsSeung Yun, Sang Hun Kim, Min Kyu Lee
Life of this patent
Estimating the term…
Abstract
Provided is a zero user interface (UI)-based automatic interpretation method including receiving a plurality of speech signals uttered by a plurality of users from a plurality of terminal devices, acquiring a plurality of speech energies from the plurality of received speech signals, determining main speech signal uttered in a current utterance turn among the plurality of speech signals by comparing the plurality of acquired speech energies, and transmitting an automatic interpretation result acquired by performing automatic interpretation on the determined main speech signal to the plurality of terminal devices.
Claims16
Automatic interpretation method performed by a server communicating with a plurality of terminal devices including a first terminal device of a first user and a second terminal device of a second user located close to each other, the automatic interpretation method comprising:
- receiving a plurality of speech signals uttered by a plurality of users from a plurality of terminal devices;
- acquiring a plurality of speech energies from the plurality of received speech signals;
- determining a main speech signal uttered in a current utterance turn among the plurality of speech signals by comparing the plurality of acquired speech energies;
- and
- transmitting an automatic interpretation result acquired by performing automatic interpretation on the determined main speech signal to the plurality of terminal devices,
- wherein further comprising,
- before receiving the plurality of voice signals,
- performing pairing between the first terminal device and the second terminal device by a short-range wireless communication;
- exchanging language information required for automatic interpretation by the paired first and second user terminal devices;
- determining, by the first terminal device or the second terminal device, whether automatic interpretation is possible for a language used by a user of the other terminal device based on the exchanged language information;
- and
- when the automatic interpretation is possible, transmitting, by the first terminal device or the second terminal device, a connection success message to the server to establish a communication connection between the server and the first and second terminal devices, and
- wherein the determining of a main speech signal comprises:
- determining a reference speech signal among the remaining speech signals;
- and
- canceling noise of the main speech signal by using a noise signal of the main speech signal and using a ratio of a difference in power level between a estimated speech signal and the main speech signal and a difference in power level between an estimated noise signal and the noise signal.
An automatic interpretation server communicating with a plurality of terminal devices including a first terminal device of a first user and a second terminal device of a second user located close to each other, the automatic interpretation server being implemented as a computing device including at least one processor, a memory, and a system bus connecting the at least one processor and the memory, the automatic interpretation server comprising:
- a communication unit configured to receive a plurality of speech signals from a user terminal of each terminal device under the control of the at least one processor;
- a speech energy calculating unit configured to calculate a plurality of speech energies from the plurality of received speech signals under the control of the at least one processor;
- a speaker determining unit configured to determine a speech signal of a speaker among the plurality of speech signals by comparing the plurality of acquired speech energies under the control of the at least one processor;
- a noise canceling processing unit configured to cancel noise of the speech signal of the speaker under the control of the at least one processor;
- and
- an automatic interpreting unit configured to transmit an automatic interpretation result acquired by performing an automatic interpretation on the noise-free speech signal of the speaker to the plurality of terminal devices through the communication unit under the control of the at least one processor,
- wherein the communication unit receives a connection success message from any one of the first terminal device and the second terminal device paired by a short-range wireless communication,
- wherein the communication unit, the first terminal device, and the second terminal device establish a communication connection according to the reception of the connection success message, and
- wherein the noise canceling processing unit cancels noise of the speech signal of the speaker using a noise signal of the speech signal and using a ratio of a difference in power level between an estimated speech signal and the speech signal and a difference in power level between an estimated noise signal and the noise signal.
Dependencies are inferred from the claim text.