-
公开(公告)号：GB2424742A
公开(公告)日：2006-10-04
申请号：GB0506528
申请日：2005-03-31
Applicant: IBM
Inventor： DOW BARRY NEIL , LAWRENCE STEPHEN GRAHAM COPING , PICKERING JOHN BRIAN
IPC: G10L15/14 , G10L15/00 , G10L15/065 , G10L15/187
Abstract: A system for automatic recognition of foreign speakers analyses (402) a speech sample and attempts to match the resulting signal to one of a plurality of predetermined sounds to produce recognition, it is determined whether a gap exists in a table of predetermined sounds in a predetermined language and, if a gap exists, a sound from a position in the table near the gap is substituted. This automatic substitution of known foreign pronunciation characteristics improves and modifies the output from standard, monolingual automatic speech recognition (ASR). There is no requirement to implement adaptation or to impose additional manual modification of the baseform pool on the application developer. In addition, the danger of increased ambiguity is removed by introducing an explicit accent and/or language checker (408) which queries known differences across accents.
-
公开(公告)号：GB2409560A
公开(公告)日：2005-06-29
申请号：GB0329761
申请日：2003-12-23
Applicant: IBM
Abstract: A speech recognition system, for instance in a car, has: a generic speech model 118 for comparison with the user speech input; means for identifying a personal speech model, for instance in a mobile phone 104, connected to the system; means for receiving personal speech model components, for instance a bluetooth connection; means 120 for updating the generic speech model using the received personal speech model components; and means 116 for performing speech recognition on user speech using the updated generic speech model.
-
公开(公告)号：GB2524302A
公开(公告)日：2015-09-23
申请号：GB201404964
申请日：2014-03-20
Applicant: IBM
Inventor： XU FENGLIAN , DOW BARRY NEIL
Abstract: The method carried out at a security application (e.g. at a telephone device) includes: activating a security process during an active telephone call to a user received at a first call identifier; accessing registered user service providers to obtain contact details of a registered service provider purporting to be the origin of the active telephone call; sending a query to the obtained contact details of the registered service provider, wherein the query includes the first call identifier; and receiving a returned query result confirming or denying that the telephone call is from the registered service provider. Embodiments of the invention include a method for verifying a telephone caller origin carried out at a service provider server, comprising: receiving a query at a service provider requesting verification that an active call is genuine call from or on behalf of the service provider, wherein the query includes a first call identifier of the number at which the call was received; checking active call logs to ascertain if there is a current call to the first call identifier from or on behalf of the service provider; returning a query result confirming or denying that the call is from the registered service provider.
-
公开(公告)号：GB2409560B
公开(公告)日：2007-07-25
申请号：GB0329761
申请日：2003-12-23
Applicant: IBM
Abstract: A method and apparatus for updating a speech model on a multi-user speech recognition system with a personal speech model for a single user. A speech recognition system, for instance in a car, can include a generic speech model for comparison with the user speech input. A way of identifying a personal speech model, for instance in a mobile phone, is connected to the system. A mechanism is included for receiving personal speech model components, for instance a BLUETOOTH connection. The generic speech model is updated using the received personal speech model components. Speech recognition can then be performed on user speech using the updated generic speech model.
-
-
-
Search Results
4
records
(took 0.017 seconds)
