摘要:
A method of accessing a dial-up service involves the following steps: (a) dialing a service number (172); (b) speaking a number of digits to form a first utterance (174); (c) recognizing the digits using speaker independent speaker recognition (176); (d) when a user has used the dial-up service previously, verifying the user based on the first utterance using a speaker verification system (178); (e) when the user cannot be verified, requesting the user enter a personal identification number (182); and (f) when the personal identification number is valid (184), providing access to the dial-up service (186).
摘要:
A system (10) and method (40) for providing audible caller information to telephone service subscribers is presented. The system (10) includes a pre-processor (28) that converts textual caller information from a first data format to a second data format suitable for text-to-speech synthesis (TTS). The pre-processor (28) can be incorporated in a service node/intelligent peripheral (SN/IP) (24) in an advanced intelligent network (AIN). In this configuration, the pre-processor (28) can be used to convert caller-ID with name database entries into a predetermined TTS format. The TTS formatted information can be provided to a TTS synthesized (30) included in the SN/IP (24). In conjunction with a switching service point (SSP) (20), the pre-processor (28) can provide a talking call-waiting feature to subscribers with significantly improved intelligibility.
摘要:
A system for utilizing multiple simultaneous communication channels has a control and display system (16). A modem (12) is controlled by the control and display system (16) and connected to a telephone line (14). A multiplexer (18) is connected to the modem (12) and multiplexes a plurality of outgoing data streams in a predefined format and demultiplexes an incoming data stream from the modem (12). A speech encoding system (20) generates a plurality of speech packets to form one of the plurality of outgoing data streams. A telephone line control system (22) generates a plurality of control packets forming one of the plurality of outgoing data streams and an information channel (24) forms one of the plurality of outgoing data streams.
摘要:
The invention uses the advanced intelligent network to provide caller identification for calls placed over the internet (24). A long distance call placed with an internet carrier results in the originating SSP (14) forwarding the call to an originating POP (22) for the internet carrier. The caller ID information is routed through the signaling system 7 network (16) to the SSP (32) in the terminating network. The call is routed to a terminating POP (26) and then to the SSP (32) in the terminating network. The SSP (32) inserts the caller ID information received through the SS7 network (16) and routes the call to the terminating line (30).
摘要:
A speaker verification method consist of the following steps: (1) generating a code book (42) covering a number of speakers having a number of training utterances for each of the speakers; (2) receiving a number of test utterances (44) from a speaker; (3) comparing (46) each of the test utterances to each of the training utterances for the speaker to form a number of decisions, one decision for each of the number of test utterances; (4) weighting each of the decisions (48) to form a number of weighted decisions; and (5) combining (50) the plurality of weighted decisions to form a verification decision (52).
摘要:
A speech reference enrollment method involves the following steps: (a) requesting a user speak a vocabulary word; (b) detecting a first utterance (354); (c) requesting the user speak the vocabulary word; (d) detecting a second utterance (358); (e) determining a first similarity between the first utterance and the second utterance (362); (f) when the first similarity is less than a predetermined similarity, requesting the user speak the vocabulary word; (g) detecting a third utterance (366); (h) determining a second similarity between the first utterance and the third utterance (370); and (i) when the second similarity is greater than or equal to the predetermined similarity, creating a reference (364).