Systems and methods for TV navigation with compressed voice-activated commands

• US 7,321,857 B2
• Filed: 01/10/2005
• Issued: 01/22/2008
• Est. Priority Date: 12/03/2001
• Status: Expired due to Term

• Current Assignee: Synamedia Limited
• Original Assignee: Scientific-Atlanta Incorporated (Cisco Systems, Inc.)
• Inventors: Rodriguez, Arturo A., Sedacca, David A., Garcia, Albert
• Primary Examiner(s): Storm; Donald L.
• Application Number:
  US11/032,438
• Publication Number:
  US 20050144009A1
• Time in Patent Office: 1,107 Days
• Field of Search: None
• US Class Current: 704/275
• 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 method, apparatus and system that receives speech commands at a remote control device microphone, digitizes those input speech commands, compresses the digitized speech commands, multiplexes control commands with the compressed digitized speech commands, and transmits the compressed digitized speech commands to an electronic device, such as a digital home communication terminal (DCHT). The electronic device decompresses and interprets the speech commands to allow the remote control operator to control the electronic device. Because speech recognition is performed at the electronic device, rather than at the remote control device, the remote control does not have to interpret and transmit infrared signals that represent user commands. This simplifies the processing and voice recognition capabilities required by the remote control. Additionally, because the electronic device processes the digitized voice received from the remote control device, the electronic device can negate the effect of sounds, such as television audio, likely captured by the microphone on the remote control device. This results in a great capability of the electronic device to interpret user commands.

Claims

1. A method of using voice activated commands to instruct electronic equipment to perform one or more functions, comprising:

receiving at a remote control device speech representing a user command;

digitizing the speech at the remote control device;

compressing the digitized speech;

multiplexing the compressed digitized speech with control commands to produce a data transport stream comprising a control stream and a speech stream;

transmitting the data transport stream wirelessly to the electronic equipment;

receiving the data transport stream at the electronic equipment;

demultiplexing the data transport stream to produce the compressed digitized speech and the control commands;

decompressing the compressed digitized speech; and

performing at the electronic equipment a function based upon a stored instruction associated with the decompressed digitized speech.

2. The method of claim 1, wherein receiving at the remote control device speech representing the user command comprises receiving at a remote control device user instructions and unwanted ambient audio,

wherein the unwanted ambient audio comprises background noise generated by sources other than the electronic equipment,

wherein transmitting the compressed digitized speech wirelessly comprises:

transmitting the compressed digitized speech over a wireless communication channel for digitized media;

transmitting the digitized speech via a transmission antenna; and

transmitting the compressed digitized speech over a wireless media radio-frequency communication channel,

wherein receiving the compressed digitized speech comprises receiving the compressed digitized speech via a receiver antenna,

wherein the electronic equipment is a digital home communication terminal.

3. The method of claim 1, further comprising comparing a portion of the decompressed digitized speech to a dictionary of speech segments, where the dictionary of speech segments is pre-programmed by a user,

wherein the comparing the portion of the decompressed digitized speech to the dictionary of speech segments further comprises producing a matching score representing the likelihood of a match between the portion of the decompressed digitized speech and a speech segment in the dictionary of speech segments.

4. The method of claim 2, further comprising:

subtracting the unwanted ambient audio from the decompressed digitized speech, wherein the step of subtracting the unwanted ambient audio from the decompressed digitized speech occurs before a portion of the decompressed digitized speech is compared to a dictionary of speech segments, wherein the unwanted ambient audio further comprises audio generated by the electronic equipment and is emitted by a speaker associated with a television set and corresponds to a program broadcast by a TV station;

storing a time-shifted delay version of the unwanted ambient audio in memory in the electronic equipment, wherein the time-shifted delay version of the unwanted ambient audio stored in the memory is matched with the unwanted ambient audio in the decompressed digitized speech;

storing the unwanted ambient audio generated by the electronic equipment in the memory in the electronic equipment, wherein the unwanted ambient audio stored in the memory is updated with new unwanted ambient audio as time progresses, and wherein the new unwanted ambient audio comprises television program audio;

identifying a dictionary speech segment associated with a portion of the decompressed digitized speech;

assigning a matching score to each portion of decompressed digitized speech associated with the dictionary speech segment;

rejecting at least a portion of decompressed digitized speech representing a user command when each matching score falls below a threshold value;

requesting a user to repeat the user command;

graphically displaying a function associated with the identified dictionary speech segment; and

audibly identifying the function associated with the identified dictionary speech segment.

5. The method of claim 1, further comprising:

querying a user for said speech representing a user command, wherein querying comprises graphically requesting the user for said speech representing a user command, wherein querying further comprises audibly requesting the user for said speech representing a user command.

6. The method of claim 1, wherein the control stream includes at least one of a start command, a stop command, a standby command, and a no-active-speech-frame command.

7. The method of claim 6, wherein the start command followed by the stop command demarcates a voice-activated command received while an enable microphone function is activated.

8. The method of claim 6, further comprising:

generating the start command upon receiving speech representing the user command while an enable microphone function is activated.

9. The method of claim 6, further comprising:

generating the standby command while no speech is received.

10. The method of claim 6, further comprising:

determining whether energy of received audio samples at a remote control device is below a threshold; and

generating the no-active-speech-frame command while the energy is below the threshold.

11. The method of claim 6, further comprising:

detecting, at a remote control device, when the amplitude of each of a plurality of received audio samples is below a threshold; and

upon the detecting, generating the no-active-speech-frame command, the no-active-speech-frame command including a start time corresponding to the first of the received audio samples that is below the threshold.

12. The method of claim 6, further comprising:

determining, at the remote control device, whether the amplitude of each of a contiguous sequence of received audio samples is above or below a threshold;

upon detecting the amplitude is below the threshold, generating the no-active-speech-frame command, the no-active-speech-frame command including a start time corresponding to the first of the received audio samples that is below the threshold;

upon detecting the amplitude is above the threshold, terminating the no-active-speech-frame command.

13. A remote control apparatus that receives voice activated commands comprising:

a first microphone;

an enable microphone function configured to activate the first microphone such that the first microphone can receive inputs;

a processor configured to digitize inputs received at the first microphone;

a speech encoder configured to compress the digitized inputs;

a multiplexer configured to multiplex the compressed digitized inputs with control commands to produce a data transport stream comprising a control stream and a speech stream; and

a transmitter configured to wirelessly transmit the data transport stream to a device associated with the remote control apparatus.

14. The remote control apparatus of claim 13,

wherein an input comprises one of a plurality of function keys in combination with one of a plurality of voice commands,

wherein one of the plurality of voice commands effects control of a television,

wherein one of the plurality of voice commands effects control of an electronic program guide,

wherein the enable microphone function is in an active state when a user depresses a function key on the remote control apparatus,

wherein the enable microphone function comprises a spring-force level switch that is placed in an active state when a user depresses the switch,

wherein the enable microphone function is a two position on/off switch, and

wherein a function key of the plurality of function keys is selected from a group consisting of a toggle switch, a button, and a spring-force level switch.

15. The remote control apparatus of claim 13, further comprising a standby command that identifies when the enable microphone function is enabled,

wherein the standby command is generated autonomously by the remote control apparatus,

wherein the standby command is generated upon detection of the completion of the inputs, and

wherein the completion of the inputs is detected by the remote control apparatus when a level of the inputs falls below a first threshold value.

16. The remote control apparatus of claim 13, further comprising a second microphone that is operative to assist in canceling noise received by the first microphone, wherein the processor is operative to digitize inputs received by the second microphone.

17. The remote control apparatus of claim 13,

wherein the speech encoder encodes speech received at the first microphone when a level of the inputs is above a threshold value established by the processor, and

the control commands comprise a standby command that identifies when the enable microphone function is enabled.

18. A home communication terminal that receives voice activated commands and, based upon the voice activated commands, instructs electronic equipment to perform functions, comprising:

a receiver that receives a data transport stream comprising a control stream and a speech stream from a remote device, wherein the speech stream includes encoded digitized signals representing a voice activated command;

a demultiplexor that demultiplexes the data transport stream to produce the

encoded digitized signals and control commands;

a speech decoder that decodes the encoded digitized signals;

a memory that stores a dictionary of terms derived from voice samples of a user associated with the home communication terminal and a portion of the decoded digitized signals;

an audio buffer that stores audio signals broadcast by a device in electrical communication with the receiver;

a processor that eliminates stored audio signals from the decoded digitized signals, such that the resulting decoded digitized signals do not contain audio signals broadcast by the device in electrical communication with the receiver; and

a comparison component that matches at least a portion of the resulting decoded digitized signals to commands representing a function the home communication terminal is operative to perform.

19. The home communication terminal of claim 18, further comprising:

an electronic program guide (EPG) application controllable by the remote device via the voice activated command; and

program information stored in the memory and accessible by the EPG application,

wherein each term is associated with the voice activated commands representing the function that the home communication terminal is operative to perform, wherein each term is associated with a machine state of the EPG application.

20. The home communication terminal of claim 18, further comprising a training procedure application,

wherein the dictionary of terms is constructed during a training procedure effected by the processor in conjunction with the training procedure application,

wherein each term in the dictionary of terms is associated with commands representing a navigation task that the home communication terminal is operative to perform,

wherein the training procedure application averages multiple versions of signals representing the voice activated command input during the training procedure,

wherein the training procedure application stores in the dictionary of terms the multiple versions of the signals representing the voice activated command input during the training procedure,

wherein each version of the signals representing the voice activated command input during the training procedure is associated with a television command,

wherein each version of the signals representing the voice activated command input during the training procedure is associated with an electronic program guide application command,

wherein the dictionary of terms is stored in the memory of the home communication terminal,

wherein the memory further comprises a dictionary of terms, wherein each term is associated with the commands representing the function that the home communication terminal is operative to perform, and

wherein each term is associated with a television function.