End-of-turn detection in spoken dialogues

Patent metadata

Field	Value
Publication number	US-2020243073-A1
Application number	US-201916257566-A
Country	US
Kind code	A1
Filing date	Jan 25, 2019
Priority date	Jan 25, 2019
Publication date	Jul 30, 2020
Grant date	—

Abstract

Systems, computer-implemented methods, and computer program products that can facilitate predicting a source of a subsequent spoken dialogue are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a speech receiving component that can receive a spoken dialogue from a first entity. The computer executable components can further comprise a speech processing component that can employ a network that can concurrently process a transition type and a dialogue act of the spoken dialogue to predict a source of a subsequent spoken dialogue.

First claim

What is claimed is:

1 . A system, comprising:
a memory that stores computer executable components; a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a speech receiving component that receives a spoken dialogue from a first entity; and
a speech processing component that employs a network that concurrently processes a transition type and a dialogue act of the spoken dialogue to predict a source of a subsequent spoken dialogue.

2 . The system of claim 1 , wherein the network is a multi-task network, and wherein the system further comprises a network optimizing component that optimizes the multi-task network by employing a plurality of speech labels to predict the source of the subsequent spoken dialogue.

3 . The system of claim 2 , wherein the multi-task network is a multi-task neural network, and wherein the plurality of speech labels comprises an optimizing data set.

4 . The system of claim 2 , wherein the network optimizing component further employs a joint loss function to reconcile the transition type and the dialogue act.

5 . The system of claim 1 , wherein the speech processing component determines at least one prediction of the source of the subsequent spoken dialogue, and wherein the speech processing component selects a prediction of the at least one prediction for output.

6 . The system of claim 1 , wherein the speech processing component determines the dialogue act to determine the transition type.

7 . The system of claim 1 , wherein the speech processing component determines a dialogue act timing based on the spoken dialogue.

8 . The system of claim 1 , wherein the transition type comprises a hold function that predicts that the first entity will provide the subsequent spoken dialogue.

9 . The system of claim 1 , wherein the transition type comprises a switch function that predicts that a second entity, different from the first entity, will provide the subsequent spoken dialogue.

10 . A computer-implemented method, comprising:
receiving, by a system operatively coupled to a processor, a spoken dialogue from a first entity; and predicting, by the system, a source of a subsequent spoken dialogue by employing, by the system, a network that concurrently processes a transition type and a dialogue act.

11 . The computer-implemented method of claim 10 , wherein the network is a multi-task network, and wherein the computer-implemented method further comprises optimizing, by the system, the multi-task network by employing a plurality of speech labels to predict the source of the subsequent spoken dialogue.

12 . The computer-implemented method of claim 11 , wherein the multi-task network is a multi-task neural network, and wherein the plurality of speech labels comprises an optimizing data set.

13 . The computer-implemented method of claim 11 , wherein the optimizing the multi-task network further employs a joint loss function to reconcile the transition type and the dialogue act.

14 . The computer-implemented method of claim 10 , wherein the predicting the source of the subsequent spoken dialogue comprises determining, by the system, at least one prediction of the source of the subsequent spoken dialogue, and wherein the computer-implemented method further comprises selecting, by the system, a prediction of the at least one prediction for output.

15 . The computer-implemented method of claim 10 , wherein the dialogue act determines the transition type.

16 . The computer-implemented method of claim 10 , wherein the network determines a dialogue act timing based on the spoken dialogue.

17 . The computer-implemented method of claim 10 , wherein the transition type comprises a hold function that predicts that the first entity will provide the subsequent spoken dialogue.

18 . The computer-implemented method of claim 10 , wherein the transition type comprises a switch function that predicts that a second entity, different from the first entity, will provide the subsequent spoken dialogue.

19 . A computer program product facilitating predicting a source of a subsequent spoken dialogue, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
receive, by the processor, a spoken dialogue from a first entity; and predict, by the processor, the source of the subsequent spoken dialogue by employing, by the processor, a network that concurrently processes a transition type and a dialogue act.

20 . The computer program product of claim 19 , wherein the network is a multi-task neural network, and wherein the program instructions are further executable by the processor to cause the processor to optimize, by the processor, the multi-task neural network by employing a plurality of speech labels to predict the source of the subsequent spoken dialogue.

Assignees

• IBM
• Univ Michigan Regents

Inventors

• Polymenakos Lazaros
• Dimitriadis Dimitrios B
• Aldeneh Zakaria
• Mower Provost Emily

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06F40/35 Primary

  Discourse or dialogue representation · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title