Simplified decoding of voice commands using control planes

• US 9,495,969 B2
• Filed: 07/31/2014
• Issued: 11/15/2016
• Est. Priority Date: 12/03/2001
• Status: Expired due to Term

• Current Assignee: Synamedia Limited
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Rodriguez, Arturo A., Sedacca, David A., Garcia, Albert
• Primary Examiner(s): Sirjani, Fariba
• Application Number:
  US14/447,821
• Publication Number:
  US 20140343951A1
• Time in Patent Office: 838 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G08C 2201/31 Voice input
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 19/00 Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis in musical instruments G10H
• CPC Class Codes: G10L 19/008 Multichannel audio signal coding or decoding using interchannel correlation to reduce redundancy, e.g. joint-stereo, intensity-coding or matrixing
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/42206 characterized by hardware details
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58

Abstract

A received transport stream may be demultiplexed into a compressed audio stream and a control stream. The compressed audio stream may be decoded. Audio corresponding to a tuned program may be stored. The stored audio may be separated from the compressed audio stream by subtracting the stored audio from the decoded audio stream, until a no-active-speech command is found in the control stream. Responsive to the no-active-speech command, the subtracting may be omitted for a period corresponding to a duration of the no-active-speech command.

Claims

1. A method performed in a digital home communication terminal (DHCT), the method comprising:

demultiplexing a received transport stream into a compressed audio stream and a control stream;

decoding the compressed audio stream;

storing audio corresponding to a tuned program;

separating the stored audio from the compressed audio stream by subtracting the stored audio from the decoded audio stream, until a no-active-speech command is found in the control stream, wherein the no-active-speech command is received from a digital signal processor (DSP) in between a start command and a stop command representing a gap between spoken words, wherein the DSP is configured to compare an energy level of the compressed audio stream with a predetermined threshold value to determine the gap; and

responsive to the no-active-speech command, omitting the subtracting for a period corresponding to a duration of the no-active-speech command.

2. The method of claim 1, further comprising:

receiving the transport stream from a remote control.

3. The method of claim 1, wherein the decoding begins upon finding the start command in the control stream.

4. The method of claim 1, wherein the decoding ends upon finding the stop command in the control stream.

5. The method of claim 1, the separating further comprising subtracting samples of the stored audio from a program buffer from the samples of the decoded audio stream from a speech buffer, the method further comprising:

responsive to the no-active-speech command, advancing a consumption index in the program buffer by an amount corresponding to a duration of the no-active-speech command.

6. The method of claim 1, the method further comprising storing a start and length of the no-active-speech command, wherein the omitting utilizes the start and the length.

7. A system comprising:

a microphone for receiving a plurality of inputs;

a digital signal processor (DSP) configured to generate a no-active-speech command in between a start command and a stop command representing a gap between spoken words, wherein the DSP configured to compare an energy level of the compressed audio stream with a predetermined threshold value to determine the gap;

a multiplexer for multiplexing the plurality of inputs with one or more control commands to produce a data stream; and

a transmitter for transmitting the data stream to a DHCT, wherein the plurality of inputs are configured to effect the no-active-speech command at the DHCT upon receipt.

8. The system of claim 7, wherein the no-active speech command is configured to omit a subtraction function for a period corresponding to the duration of the no-active speech command.

9. The system of claim 8, further comprising at least one processor for digitizing the plurality of inputs.

10. The system of claim 8, wherein the transmitter transmits the data stream over a wireless network.

11. The system of claim 7, further comprising an enable microphone function, wherein the enable microphone function activates the microphone for receipt of one or more inputs.

12. The system of claim 8, further comprising a processor to create a first control command upon detection of the no-active-speech command.

13. A method comprising:

receiving an audio signal;

comparing, by a digital signal processor (DSP), an energy level of the compressed audio stream with a predetermined threshold value to determine a gap between spoken words in the audio signal;

generating, by the DSP, a no-active-speech command in between a start command and a stop command, wherein the no-active-speech command represents the determined gap;

multiplexing control commands with the audio signal, wherein at least one command is the no-active-speech command;

transmitting a data stream comprising the multiplexed control commands and the audio signal to a DHCT;

subtracting the audio signal from the data stream until the no-active-speech command is located; and

omitting the subtracting for a period corresponding to a duration of the no-active-speech command.

14. The method of claim 13, wherein the data stream is transmitted as a stream of encoded, digitized signals.

15. The method of claim 13, wherein the data stream is transmitted as part of a program to train voice activation software.

16. The method of claim 13, wherein the audio signal comprises one or more voice commands provided by a user.

17. The method of claim 13, wherein the subtraction begins upon finding the start command in the control commands.

18. The method of claim 13, further comprising decoding the data stream with at least one speech decoder.

19. The method of claim 18, wherein decoding the data stream ends upon finding the stop command in the control commands.

20. The method of claim 18, further comprising storing decoded audio signals in a first audio buffer.