公开(公告)号：EP1358650A4

公开(公告)日：2008-03-19

申请号：EP02724896

申请日：2002-01-31

Applicant: IBM

Inventor： MAES STEPHANE H ,  NETI CHALAPATHY V

IPC: G06F3/00 ,  G06T1/00 ,  B60K28/06 ,  G06F3/01 ,  G06F3/033 ,  G06F3/048 ,  G06F9/45 ,  G06F17/00 ,  G06K9/00 ,  G06T7/00 ,  G06T7/20 ,  G08B21/06 ,  G10L15/22 ,  G10L15/24

CPC classification number: G06K9/00248 ,  G06F3/0481 ,  G10L15/24 ,  Y10S715/966

Abstract: Systems and methods are provided for performing focus detection, referential ambiguity resolution and mood classification in accordance with multi-modal input data, in varying operating conditions, in order to provide an effective conversational computing environment for one or more users.

公开(公告)号：EP0781833A3

公开(公告)日：1998-09-23

申请号：EP96308906

申请日：1996-12-09

Applicant: IBM

Inventor： NETI CHALAPATHY V

IPC: G10L15/02 ,  G10L15/20 ,  C10L9/00

CPC classification number: G10L15/02 ,  G10L15/20

Abstract: A method for noise-robust speech processing with cochlea filters within a computer system is disclosed. This invention provides a method for producing feature vectors from a segment of speech, that is more robust to variations in the environment due to additive noise. A first output is produced by convolving (50) a speech signal input with spatially dependent impulse responses that resemble cochlea filters. The temporal transient and the spatial transient of the first output is then enhanced by taking a time derivative (52) and a spatial derivative (54), respectively, of the first output to produce a second output. Next, all the negative values of the second output are replaced (56) with zeros. A feature vector is then obtained (58) from each frame of the second output by a multiple resolution extraction. The parameters for the cochlea filters are finally optimized by minimizing the difference between a feature vector generated from a relatively noise-free speech signal input and a feature vector generated from a noisy speech signal input.

公开(公告)号：WO2004059536A3

公开(公告)日：2004-12-29

申请号：PCT/US0340726

申请日：2003-12-19

Applicant: IBM ,  ADAMS HUGH W JR ,  IYENGAR GIRIDHAREN ,  LIN CHING-YUNG ,  NETI CHALAPATHY V ,  SMITH JOHN R ,  TSENG BELLE L

Inventor： ADAMS HUGH W JR ,  IYENGAR GIRIDHAREN ,  LIN CHING-YUNG ,  NETI CHALAPATHY V ,  SMITH JOHN R ,  TSENG BELLE L

IPC: G06F17/24 ,  G06F17/30 ,  G06F3/033

CPC classification number: G06F17/30038 ,  G06F17/241

Abstract: A manual annotation system of multi-modal characteristics in multimedia files. There is provided an arrangement for selection an observation modality of video with audio, video without audio, audio with video, or audio without video, to be used to annotate multimedia content. While annotating video or audio features is isolation results in less confidence in the identification of features, observing both audio and video simultaneously and annotating that observation results in a higher confidence level.

公开(公告)号：CA2507248A1

公开(公告)日：2004-07-15

申请号：CA2507248

申请日：2003-12-19

Applicant: IBM

Inventor： SMITH JOHN R ,  NETI CHALAPATHY V ,  LIN CHING-YUNG ,  ADAMS HUGH W JR ,  IYENGAR GIRIDHAREN ,  TSENG BELLE L

IPC: G06F17/24 ,  G06F17/30 ,  G06F3/033

Abstract: A manual annotation system of multi-modal characteristics in multimedia file s. There is provided an arrangement for selection an observation modality of video with audio, video without audio, audio with video, or audio without video, to be used to annotate multimedia content. While annotating video or audio features is isolation results in less confidence in the identification of features, observing both audio and video simultaneously and annotating th at observation results in a higher confidence level.

公开(公告)号：HK1063371A1

公开(公告)日：2004-12-24

申请号：HK04106079

申请日：2004-08-13

Applicant: IBM

Inventor： MAES STEPHANE H ,  NETI CHALAPATHY V

IPC: G06F3/00 ,  G06T1/00 ,  G06F3/01 ,  G09G20060101 ,  G06F3/033 ,  G06F3/048 ,  G06F9/45 ,  G06F17/00 ,  G06K9/00 ,  G06T7/00 ,  G06T7/20 ,  G10L15/22 ,  G10L15/24

Abstract: Systems and methods are provided for performing focus detection, referential ambiguity resolution and mood classification in accordance with multi-modal input data, in varying operating conditions, in order to provide an effective conversational computing environment for one or more users.

公开(公告)号：AU2003297416A1

公开(公告)日：2004-07-22

申请号：AU2003297416

申请日：2003-12-19

Applicant: IBM

Inventor： ADAMS HUGH W JR ,  IYENGAR GIRIDHAREN ,  LIN CHING-YUNG ,  NETI CHALAPATHY V ,  SMITH JOHN R ,  TSENG BELLE L

IPC: G06F17/24 ,  G06F17/30 ,  G06F3/033

Abstract: A manual annotation system of multi-modal characteristics in multimedia files. There is provided an arrangement for selection an observation modality of video with audio, video without audio, audio with video, or audio without video, to be used to annotate multimedia content. While annotating video or audio features is isolation results in less confidence in the identification of features, observing both audio and video simultaneously and annotating that observation results in a higher confidence level.

公开(公告)号：CA2437164A1

公开(公告)日：2002-08-15

申请号：CA2437164

申请日：2002-01-31

Applicant: IBM

Inventor： MAES STEPHANE H ,  NETI CHALAPATHY V

IPC: G06T1/00 ,  G06F3/00 ,  G06F3/01 ,  G06F3/033 ,  G06F3/048 ,  G06F9/45 ,  G06F17/00 ,  G06K9/00 ,  G06T7/00 ,  G06T7/20 ,  G10L15/22 ,  G10L15/24 ,  G06F3/16

Abstract: This is a method provided for performing focus detection, ambiguity resoluti on and mood classification (815) in accordance with multi-modal input data, in varying operating conditions, in order to provide an effective conversationa l computing environment (418, 422) for one or more users (812).