Simplified decoding of voice commands using control planes
View Patent ↗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.
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.