Non-dialogue-based Learning Apparatus and Dialogue-based Learning Apparatus

• US 20100250241A1
• Filed: 08/29/2008
• Published: 09/30/2010
• Est. Priority Date: 08/31/2007
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company), National Institute of Information and Communications Technology
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company), National Institute of Information and Communications Technology
• Inventors: Kimura, Noriyuki, Nakano, Mikio, Funakoshi, Kotaro, Iwahashi, Naoto
• Granted Patent: US 8,868,410 B2
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

The invention provides a dialogue-based learning apparatus through dialogue with users comprising: a speech input unit (10) for inputting speeches; a speech recognition unit (20) for recognizing the input speech; and a behavior and dialogue controller (30) for controlling behaviors and dialogues according to speech recognition results, wherein the behavior and dialogue controller (30) has a topic recognition expert (34) to memorise contents of utterances and to retrieve the topic that best matches the speech recognition results, and a mode switching expert (35) to control mode switching in accordance with a user utterance, wherein the mode switching expert switches modes in accordance with a user utterance, wherein the topic recognition expert registers a plurality words in the utterance as topics in first mode, performs searches from among the registered topics, and selects the maximum likelihood topic in second mode.

Claims

1. A non-dialogue-based learning apparatus, comprising:

a speech input unit for inputting speeches;

a speech recognition unit for recognizing the input speech; and

a behavior and dialogue controller for controlling behaviors and dialogues according to speech recognition results,

wherein the behavior and dialogue controller has a topic recognition expert to memorise contents of utterances and to retrieve the topic that best matches the speech recognition results, and a mode switching expert to control mode switching,

wherein the mode switching expert switches modes in accordance with a user utterance,

wherein the topic recognition expert registers a plurality words in the utterance as topics in first mode, performs searches from among the registered topics, and selects the maximum likelihood topic in second mode.

2. The non-dialogue-based learning apparatus of claim 1, wherein the topic recognition expert generates a word graph as a topic in the first mode.

3. The non-dialogue-based learning apparatus of claim 2, wherein a phoneme of an unknown word are substituted for the word graph of a known word and/or combination of known words having a similar phoneme sequence in a dictionary if a user utterance includes a plurality of words undefined in the dictionary.

4. An dialogue-based learning apparatus through dialogue with users, comprising:

a speech input unit for inputting speeches;

a speech recognition unit for recognizing the input speech; and

a behavior and dialogue controller for controlling behaviors and dialogues according to speech recognition results,

wherein the behavior and dialogue controller has a topic recognition expert to memorise contents of utterances and to retrieve the topic that best matches the speech recognition results, and a mode switching expert to control mode switching,

wherein the mode switching expert switches modes in accordance with a user utterance,

wherein the topic recognition expert registers a plurality words in the utterance as topics in first mode, performs searches from among the registered topics, and selects the maximum likelihood topic in second mode.

5. The dialogue-based learning apparatus of claim 4, wherein the topic recognition expert generates a word graph as a topic in the first mode.

6. The dialogue-based learning apparatus of claim 5, wherein a phoneme of an unknown word are substituted for the word graph of a known word and/or combination of known words having a similar phoneme sequence in a dictionary if a user utterance includes a plurality of words undefined in the dictionary.