Speech recognition method of and system for determining the status of an answered telephone during the course of an outbound telephone call

• US 6,990,179 B2
• Filed: 08/31/2001
• Issued: 01/24/2006
• Est. Priority Date: 09/01/2000
• Status: Expired due to Term

• Current Assignee: Eliza Corporation (Gainwell Technologies LLC)
• Original Assignee: Eliza Corporation (Gainwell Technologies LLC)
• Inventors: Kroeker, John, Merrow, Lucas, Boulanov, Oleg, Drane, Alexandra, Quibria, Nasreen, Robinson, Michael R.
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): ELAHEE, MD S
• Application Number:
  US09/945,282
• Publication Number:
  US 20020051522A1
• Time in Patent Office: 1,607 Days
• Field of Search: 379/88.01, 379/88.02, 379/88.03, 379/88.04, 379/201.06, 379/201.07, 379/207.02, 379/201, 379/69, 379/266.07, 379/266.08, 379/88.18, 379/88.06, 379/265.09, 379/88.26, 379/88.17, 704/270
• US Class Current: 379/69
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 1/64 Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations centralised dictation systems H04M11/10
• CPC Class Codes: H04M 1/82 Line monitoring circuits for call progress or status discrimination for detecting caller identity H04M1/573
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2203/2016 Call initiation by network rather than by subscriber
• CPC Class Codes: H04M 2203/2027 Live party detection
• CPC Class Codes: H04M 3/46 Arrangements for calling a number of substations in a predetermined sequence until an answer is obtained
• CPC Class Codes: H04M 3/487 Arrangements for providing information services, e.g. recorded voice services or time announcements
• CPC Class Codes: H04M 3/5158 in combination with automated outdialling systems devices for signalling identity of wanted subscriber H04M1/26

Abstract

A system for determining the status of an answered telephone during the course of an outbound telephone call includes an automated telephone calling device for placing a telephone call to a location having a telephone number at which a target person is listed, upon the telephone call being answered, initiating a prerecorded greeting which asks for the target person and receiving a spoken response from an answering person and a speech recognition device for performing a speech recognition analysis on the spoken response to determine a status of the spoken response. If the speech recognition device determines that the answering person is the target person, the speech recognition device initiates a speech recognition application with the target person.

Claims

1. A method of controlling and directing the status of an answered telephone during the course of an outbound telephone call, comprising:

A. placing, with an automated calling system, a telephone call to a location having a telephone number associated with a target person contained in a predetermined list of target people;

B. upon the telephone call being answered as determined by an initial spoken response, or other audio or telecommunication signals, initiating a prerecorded greeting which asks for the target person;

C. receiving a subsequent spoken response from an answering person or other audio signal and determining if said subsequent spoken response or other audio signal is being provided by an answering machine, and if not performing a speaker-independent speech recognition analysis on the subsequent spoken response to determine the meaning of subsequent the spoken response; and

D. providing subsequent any one of the following conditional responses based on the meaning of the subsequent spoken response as determined by the speaker-independent speech recognition analysis in accordance with a set of speaker-independent speech recognition enabled states of conversation including;

(1) the answering person indicates that he or she is the target person, (2) the answering person indicates that he or she is not the target person, (3) the answering person indicates that the target person is not present at the location, (4) the answering person indicates a hold request, (5) the answering person requests the identity of the caller, (6) the answering person indicates that the telephone number is not the correct number for the target person; and

(7) the speaker-independent speech recognition analysis cannot determine the meaning of the subsequent spoken response from the answering person; and

E. responding appropriately to the results of the speech recognition analysis including the following conditional responses;

a. if the meaning of the subsequent spoken response indicates that the answering person is the target person, initiating a speaker-independent speech recognition application with said the target person;

b. if the meaning of the subsequent spoken response indicates that the answering person is not the target person, initiating a prerecorded query asking for the target person, wherein, upon receiving another spoken response and determining whether the meaning of said another spoken response indicates that the target person is now on the line, further comprising initiating a speaker-independent speech recognition application with the target person;

c. if the meaning of the subsequent spoken response indicates that the target person is not present at the location, initiating a prerecorded query asking to leave a message for the target person;

d. if the meaning of the subsequent spoken response indicates that the subsequent spoken response is a hold request, entering a wait state to wait for the target person to provide yet another spoken response to the telephone call, wherein upon receiving the yet another spoken response, determining the meaning of the yet another spoken response to determine whether the target person is now on the line, and if the meaning of the yet another spoken response indicates that the target person is now on the line, further comprising initiating a speaker-independent speech recognition application with the target person;

e. if the meaning of the subsequent spoken response indicates that the subsequent spoken response is a request for the identity of the caller, initiating a prerecorded response indicating the identity of the calling party, repeating the prerecorded greeting which asks for the target person, and repeating step C through step E;

f. if the meaning of the subsequent spoken response indicates that the telephone number is not the correct number for the target person, initiating a prerecorded apology message and terminating the telephone call; and

g. if the speaker-independent speech recognition analysis cannot determine the meaning of the subsequent spoken response, repeating the prerecorded greeting which asks for the target person, and repeating step C through step E.

2. A method according to claim 1, further including detecting an answering machine upon the telephone call being answered.

3. A method according to claim 2, wherein detecting an answering machine includes:

a. upon the telephone call being answered, waiting for a predetermined time period for a spoken response;

b. upon receiving the spoken response, playing a prerecorded greeting prompt which asks for the target person;

c. while playing the prerecorded greeting prompt, attempting to detect a further spoken response in excess of a predetermined time parameter;

d. in the absence of detecting a further spoken response during the playing of the prerecorded greeting prompt, initiating a query application;

e. upon detecting a further spoken response during the playing of the prerecorded greeting prompt, terminating the playing of the prerecorded prompt; and

f. indicating that an answering machine has been detected.

4. The method of claim 3, further comprising attempting to detect a beep tone during the playing of the prerecorded greeting prompt and, upon the detection of a beep tone, interrupting the prerecorded greeting prompt and playing a prerecorded answering machine message prompt.

5. The method of claim 4, further comprising attempting to detect a beep tone during the playing of the prerecorded answering machine message prompt and, upon the detection of a beep tone, interrupting the prerecorded answering machine message prompt and replaying the prerecorded prompt.

6. A system for automatically directing and controlling an answered telephone during the course of an outbound telephone call so as to automatically initiate a speaker-independent speech recognition application with a target person, comprising:

an automated calling subsystem, for placing the automated outbound telephone call to the target person; and

an automated multi-state enabled speaker-independent speech recognition device configured to;

A. initiate a prerecorded greeting which asks for the target person upon the telephone call being answered;

B. receive a spoken response from an answering person or other audio signal and determine whether the call has been answered by an answering machine, and if not proceed to step C;

C. perform a speaker-independent speech recognition analysis on the spoken response to determine the meaning of the spoken response; and

D. provide any one of the following conditional responses based on the meaning of the spoken response as determined by the speaker-independent speech recognition analysis in accordance with a set of speaker-independent speech recognition enabled states of conversation including (1) the answering person indicates that he or she is the target person, (2) the answering person indicates that he or she is not the target person, (3) the answering person indicates that the target person is not present at the location, (4) the answering person indicates a hold request, (5) the answering person requests the identity of the caller, (6) the answering person indicates that the telephone number is not the correct number for the target person, and (7) the speaker-independent speech recognition analysis cannot determine the meaning of the spoken response from the answering person;

a. if the meaning of the spoken response indicates that the answering person is the target person, initiating a speaker-independent speech recognition application with the target person;

b. if the meaning of the spoken response indicates that the answering person is not the target person, initiating a prerecorded query asking for the target person, wherein, upon receiving a subsequent spoken response and determining whether the meaning of the subsequent spoken response indicates that the target person is now on the line, further comprising initiating a speaker-independent speech recognition application with the target person;

c. if the meaning of the spoken response indicates that the target person is not present at the location, initiating a prerecorded query asking to leave a message for the target person;

d. if the meaning of the spoken response indicates that the spoken response is a hold request, entering a wait state to wait for the target person to provide a spoken response to the telephone call, wherein upon receiving a subsequent spoken response, determining the meaning of the subsequent spoken response to determine whether the target person is now on the line, and if the meaning of the subsequent spoken response indicates that the target person is now on the line, further comprising initiating a speaker-independent speech recognition application with the target person;

e. if the meaning of the spoken response indicates that the spoken response is a request for the identity of the caller, initiating a prerecorded response indicating the identity of the calling party, repeating the prerecorded greeting which asks for the target person, and repeating B through D;

f. if the meaning of the spoken response indicates that the telephone number is not the correct number for the target person, initiating a prerecorded apology message and terminating the telephone call; and

g. if the speaker-independent speech recognition analysis cannot determine the meaning of the spoken response, repeating the prerecorded greeting which asks for the target person, and repeating B through D.

7. A system according to claim 6, wherein the automated multi-state enabled speaker-independent speech recognition device is further configured to detect an answering machine upon the telephone call being answered.

8. A system according to claim 7, wherein the automated multi-state enabled speaker-independent speech recognition device is further configured to:

a. wait for a predetermined time period for a spoken response upon the telephone call being answered;

b. play a prerecorded greeting prompt which asks for the target person upon receiving the spoken response;

c. attempt to detect a further spoken response in excess of a predetermined time parameter while playing the prerecorded greeting prompt;

d. initiate a query application in the absence of detecting a further spoken response during the playing of the prerecorded greeting prompt;

e. terminating the playing of the prerecorded prompt upon detecting a further spoken response during the playing of the prerecorded greeting prompt; and

f. indicate that an answering machine has been detected.

9. The system of claim 8, wherein the automated multi-state enabled speaker-independent speech recognition device is further configured to attempt to detect a beep tone during the playing of the prerecorded greeting prompt and, upon the detection of a beep tone, interrupting the prerecorded greeting prompt and playing a prerecorded answering machine message prompt.

10. The system of claim 9, wherein the automated multi-state enabled speaker-independent speech recognition device is further configured to attempt to detect a beep tone during the playing of the prerecorded answering machine message prompt and, upon the detection of a beep tone, interrupting the prerecorded answering machine message prompt and replaying the prerecorded prompt.