Method and apparatus for transmitting DTMF signals employing local speech recognition

• US 6,493,670 B1
• Filed: 10/14/1999
• Issued: 12/10/2002
• Est. Priority Date: 10/14/1999
• Status: Expired due to Term

• Current Assignee: Ericsson, Inc. (Telefonaktiebolaget LM Ericsson)
• Original Assignee: Ericsson, Inc. (Telefonaktiebolaget LM Ericsson)
• Inventors: Croft, Thomas M.
• Primary Examiner(s): Knepper, David D.
• Assistant Examiner(s): Azad, Abul K.
• Application Number:
  US09/418,528
• Time in Patent Office: 1,153 Days
• Field of Search: 704/251, 704/231, 704/257, 704/270, 379/88.01, 379/88.02, 379/88.03, 379/563, 379/204.01, 379/205.01, 379/207.01, 455/460, 455/550, 455/564
• US Class Current: 704/270
• CPC Class Codes: H04M 1/271 controlled by voice recognition

Abstract

A method and apparatus providing a telephone user with a manner in which to send DTMF commands during a call over a communication network by use of a speech-based user interface. The user speaks one or more words corresponding to DTMF commands, and the invention performs speech recognition on the spoken words, generates corresponding DTMF signals, and transmits the DTMF signals over the network.

Claims

1. A telephone for use by a user who speaks an utterance which is indicative of a DTMF signal the user desires to be transmitted by the telephone, the telephone comprising:

a microphone which receives the spoken utterance from the user and outputs electrical microphone signals which are indicative of the spoken utterance;

a speech recognition circuit within said telephone which receives the electrical microphone signals and outputs a speech recognition signal which identifies when the microphone signals correspond to one of a predetermined set of DTMF commands;

an input for activating the speech recognition circuit while engaged in a call;

a DTMF signal generator which receives the speech recognition signal and responds, when the speech recognition signal identifies one of the predetermined set of DTMF commands, by outputting a DTMF signal which corresponds to the identified one of the predetermined set of DTMF commands; and

means for deactivating the speech recognition circuit while engaged in a call.

2. The telephone of claim 1, wherein the input for activating the speech recognition circuit comprises a pushbutton switch which, when toggled by the user prior to the user speaking the utterance, activates the speech recognition circuit.

3. The telephone of claim 1, wherein the speech recognition circuit first waits for a microphone signal which corresponds to a predetermined activation command before outputting speech recognition signals indicative of a DTMF command.

4. The telephone of claim 1, wherein the means for deactivating the speech recognition circuit comprise a timer which waits for a predetermined period of silence after the user speaks one or more utterances indicative of one or more corresponding DTMF signals and deactivates the speech recognition circuit.

5. The telephone of claim 1, further comprising:

one or more speakers;

an audio output stage which drives the speakers;

a memory which stores speech waveforms corresponding to spoken names of the predetermined set of DTMF commands;

a speech synthesizer electrically connected to the audio output stage and the memory which reads the speech waveforms stored in the memory and plays to the user the spoken name corresponding to the DTMF signal recognized by the speech recognition circuit to provide the user with audible feedback.

6. The telephone of claim 1, further comprising:

an RF transmitter for transmitting the DTMF signal over a wireless communication network.

7. Within a telephone, a method for converting spoken utterances from a user to DTMF signals for transmission through a telecommunications network during a call, the method comprising the steps of:

activating a speech recognition circuit within the telephone while engaged in a call;

receiving a spoken utterance;

determining whether the spoken utterance corresponds to one of a predetermined set of DTMF commands;

generating a DTMF signal associated with the DTMF command when the spoken utterance is found to correspond to one of the DTMF commands;

transmitting the DTMF signal through the telecommunications network during the call;

repeating the steps of determining, generating, and transmitting; and

deactivating the speech recognition circuit while engaged in a call.

8. The method of claim 7, wherein the step of activating the speech recognition circuit comprises pressing a pushbutton switch on the telephone.

9. The method of claim 8, further comprising the step of:

playing a first audible tone through a speaker of the telephone to alert the user that the telephone is ready for the receiving step following the pressing of the push button switch and prior to the receiving step.

10. The method of claim 9, further comprising the steps of:

playing a second audible tone to the user when the steps of receiving, determining, generating, and transmitting have been completed successfully; and

playing a third audible tone distinct from the first audible tone and the second audible tone to the user when the determining step does not find a correspondence.

11. The method of claim 10, wherein the second tone is at the same audible frequency as the first tone.

12. The method of claim 8, further comprising the step of:

when the determining step finds a correspondence, playing to the user through a speaker in the telephone a pre-stored speech waveform corresponding to the spoken utterance which allows the user to confirm that the determining step was performed correctly.

13. The method of claim 7, wherein the step of determining whether the spoken utterance corresponds to one of the DTMF commands is initiated by the prior recognition of a predetermined activation command.

14. The method of claim 13, further comprising the steps of:

playing a first audible tone to the user when the determining step finds a correspondence; and

playing a second audible tone distinct from the first audible tone to the user when the determining step does not find a correspondence.

15. The method of claim 7, wherein the determining step checks the correspondence of the spoken utterance to a predetermined set of words comprising “

one,”

“

two,”

“

three,”

“

four,”

“

five,”

“

six,”

“

seven,”

“

eight,”

“

nine,”

“

zero,”

“

oh,”

“

star,”

“

asterisk,”

“

pound,” and

“

number.”

16. The method of claim 7, wherein the spoken utterance is a word from a set comprising words representing the alphabetic letters “

A”

through “

Z”

.

17. The method of claim 7, wherein the predetermined set of DTMF commands comprises the digits “

0”

through “

9”

, the character “

*”

, and the character “

#”

.

18. The method of claim 7, wherein the step of deactivating the speech recognition circuit comprises deactivating the speech recognition circuit after a timer within the telephone measures a predetermined interval of silence, and wherein the steps of generating and transmitting are performed for each of the plurality of spoken utterances which corresponds to one of the predetermined DTMF commands.