Abstract:
PROBLEM TO BE SOLVED: To provide an acoustic signal processing device capable of performing acoustic signal processing for securing a real-time property.SOLUTION: A unit 4 comprises: a human position detection part 31 for detecting the position of persons who exist inside a prescribed space; a grouping part 32 for allotting one or more persons detected by the human position detection part 31 to the groups of a predetermined number or less; a plurality of directivity control parts 34 for controlling the directivity of a microphone array 12 according to the set directivity of each one; and a directivity setting part 33 for setting the directivity of each group grouped by the grouping part 32 to the corresponding directivity control part 34.
Abstract:
PROBLEM TO BE SOLVED: To provide a process for collecting the identity of a telephone caller. SOLUTION: In one embodiment, a personalized context free grammar (CFG) (212) is created for each potential call recipient (210), and is configured to support the identification of incoming callers using speech recognition. Each CFG (212) incorporates an indication of high probability callers and probability weights in each CFG are altered accordingly. When a recipient (210) receives a call (202), the relevant CFG (212) is applied in association with a speech recognition application (222) to enable at least a preliminary identification of the caller. In another embodiment, the caller confirms the identifications. In accordance with one embodiment, a standard caller number notification service function (224) is used if possible at least to assist in a caller identification process when available. In accordance with still another embodiment, provided is an intelligent call routing function (226) using speech recognition enhanced caller identification. COPYRIGHT: (C)2005,JPO&NCIPI
Abstract:
PROBLEM TO BE SOLVED: To grasp whether to be a dubious telephone call at an early stage. SOLUTION: An IP Tel 1 transfers a received signal from the opposite speech communication party during speech communication to a voiceprint collating server 2 according to an instruction of the operator of the IP Tel 1, and receives and displays the past speech communication data of the opposite speech communication party transmitted from the voiceprint collating server 2 in response to the above transfer, the voiceprint collating server 2 receives the received signal transferred from the IP Tel 1, obtains a voiceprint from the received signal, retrieves the past speech communication data of the opposite speech communication party with the voiceprint data as a key, and transmits the retrieved speech communication data to the IP Tel 1. Thus, the operator of the IP Tel 1 can grasp whether an incoming telephone call to be a dubious telephone call at an early stage by looking at displayed contents to be helped in answer the telephone call. COPYRIGHT: (C)2005,JPO&NCIPI
Abstract:
システム(200)は、個人の身元を確認する情報に関連した音声サンプル情報を格納する記憶部(210)を含む。 システムは、VoIP(Voice over Internet Protocol)によってパケット化されるとともに呼び出し中に呼出人から得られるデジタルオーディオサンプルを使って呼出人の身元を認証するための要求を、呼出人によって呼び出される通信プラットフォーム(150/152/154)から受ける受信部(221)を含む。 さらにシステムは、デジタルオーディオサンプルを音声サンプル情報と照合し、呼出人を本人と認証する処理部(223)を含む。