A Standard Audio Encapsulation Method and Homayoon Beigi Judith - - PowerPoint PPT Presentation

a standard audio encapsulation method
SMART_READER_LITE
LIVE PREVIEW

A Standard Audio Encapsulation Method and Homayoon Beigi Judith - - PowerPoint PPT Presentation

A Standard Audio Encapsulation Method and Homayoon Beigi Judith Markowitz Beigi@RecognitionTechnologies.com Judith@JMarkowitz.com http://www.RecognitionTechnologies.com http://www.JMarkowitz.com of of Recognition Technologies, Inc. J.


slide-1
SLIDE 1

A Standard Audio Encapsulation Method

Homayoon Beigi

Beigi@RecognitionTechnologies.com http://www.RecognitionTechnologies.com

  • f

Recognition Technologies, Inc.

300 Hamilton Avenue White Plains, NY, U.S.A.

Judith Markowitz

Judith@JMarkowitz.com http://www.JMarkowitz.com

  • f
  • J. Markowitz Consultants

5801 N. Sheridan Road Chicago, IL, U.S.A.

and

slide-2
SLIDE 2

Mar 4, 2009

Starting Question to Ask

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

What Should be Standardized at This Stage of Development in Speaker Recognition?

slide-3
SLIDE 3

Mar 4, 2009

Starting Question to Ask

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

What Should be Standardized at This Stage of Development in Speaker Recognition? Audio Format? Speaker Models? Interaction with Engines? Results of Recognition?

slide-4
SLIDE 4

Mar 4, 2009

Starting Question to Ask

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

What Should be Standardized at This Stage of Development in Speaker Recognition? Audio Format?

Definitely

Speaker Models? Interaction with Engines? Results of Recognition?

slide-5
SLIDE 5

Mar 4, 2009

Starting Question to Ask

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

What Should be Standardized at This Stage of Development in Speaker Recognition? Audio Format?

Definitely

Speaker Models?

Not Yet

Interaction with Engines? Results of Recognition?

slide-6
SLIDE 6

Mar 4, 2009

Starting Question to Ask

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

What Should be Standardized at This Stage of Development in Speaker Recognition? Audio Format?

Definitely

Speaker Models?

Not Yet

Interaction with Engines? Results of Recognition?

Yes

slide-7
SLIDE 7

Mar 4, 2009

Starting Question to Ask

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

What Should be Standardized at This Stage of Development in Speaker Recognition? Audio Format?

Definitely

Speaker Models?

Not Yet

Interaction with Engines?

Yes

Results of Recognition?

Yes

slide-8
SLIDE 8

Mar 4, 2009

Large-Scale Speaker Recognition

Recognition Technologies, Inc.

Large Government Applications Financial Applications – Fraud Protection, Account Access, etc. Large Health Insurance Memberships – Access to Medical Records, etc. Telephone Order Credit Card Charges – Verify buyers in place of signature Large Corporation VoiceMail Applications Other System-Wide Applications – Requiring Remote Authentication or Customization Remote Test Proctoring – Requires continuous verification Social Security Eligibility Verification, Border Crossing, etc. – millions of participants Verification of Life Status for remote citizens – e.g. Pension plans Forensic Applications

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

slide-9
SLIDE 9

Mar 4, 2009

Goals (Audio Format Only)

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

A Basic List of Audio Formats Meeting All Interchange Requirements

slide-10
SLIDE 10

Mar 4, 2009

Goals (Audio Format Only)

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

A Basic List of Audio Formats Meeting All Interchange Requirements With Minimal Redundancy for the Sake of Clarity, Simplicity, and Compactness

slide-11
SLIDE 11

Mar 4, 2009

Goals (Audio Format Only)

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

A Basic List of Audio Formats Meeting All Interchange Requirements Preference Given to Open-Source and Royalty-Free Formats With Minimal Redundancy for the Sake of Clarity, Simplicity, and Compactness

slide-12
SLIDE 12

Mar 4, 2009

Goals (Audio Format Only)

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

A Basic List of Audio Formats Meeting All Interchange Requirements Preference Given to Open-Source and Royalty-Free Formats Ease of Adoption With Minimal Redundancy for the Sake of Clarity, Simplicity, and Compactness

slide-13
SLIDE 13

Mar 4, 2009

Goals (Audio Format Only)

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

A Basic List of Audio Formats Meeting All Interchange Requirements Preference Given to Open-Source and Royalty-Free Formats Ease of Adoption Stability of Implementation With Minimal Redundancy for the Sake of Clarity, Simplicity, and Compactness

slide-14
SLIDE 14

Mar 4, 2009

Goals (Audio Format Only)

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

A Basic List of Audio Formats Meeting All Interchange Requirements Preference Given to Open-Source and Royalty-Free Formats Ease of Adoption Stability of Implementation Relative Quality – Compared to Contenders With Minimal Redundancy for the Sake of Clarity, Simplicity, and Compactness

slide-15
SLIDE 15

Mar 4, 2009

Sampling Process

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

Sampling

Analog Signal Storage

Type Bit Rate (bps)

Periodic Multirate Cyclic Rate Random Pulse-Width Modulated

Periodic: Bit Rate (bps) is Prop. to Sampling Freq. (Hz) Multirate: Bit Rate (bps) has Indirect Rel. to Freq. (Hz)

slide-16
SLIDE 16

Mar 4, 2009

Lossless Representation – Amplitude and Frequency are Unchanged Amplitude Compression – Freq. Stays the Same, Amplitude is Represented Nonlinearly Multirate Sampling – Aggressive Variable Bitrate Compression

Audio Coding Scenarios

Recognition Technologies, Inc.

Streaming – Usually includes multirate sampling and streaming

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

slide-17
SLIDE 17

Mar 4, 2009

Lossless Representation

Audio Interchange Scenarios

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

Microsoft WAV Comes to Mind – A Wrapper which includes over 104 codecs LPCM offers all that is needed – Just need to code the header information

slide-18
SLIDE 18

Mar 4, 2009

Lossless Representation

Audio Interchange Scenarios

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

LPCM offers all that is needed – Just need to code the header information Amplitud Compression G.711 and G.711.1 ITU-T define PCMU and PCMA for 64, 80, and 96kbps ADPCM was considered, but it has many flavors and is not open source

slide-19
SLIDE 19

Mar 4, 2009

Lossless Representation

Audio Interchange Scenarios

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

LPCM offers all that is needed – Just need to code the header information Amplitud Compression G.711 and G.711.1 ITU-T define PCMU and PCMA for 64, 80, and 96kbps Multirate Sampling MP3 comes to mind – Patent driven and certainly not an open standard OGG Vorbis – Open Source and better quality as MP3 for the same bit rate

slide-20
SLIDE 20

Mar 4, 2009

Lossless Representation

Audio Interchange Scenarios

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

LPCM offers all that is needed – Just need to code the header information Amplitud Compression G.711 and G.711.1 ITU-T define PCMU and PCMA for 64, 80, and 96kbps Multirate Sampling OGG Vorbis – Open Source and better quality as MP3 for the same bit rate Streaming – Usually includes multirate sampling and streaming OGG Media Stream – Open Source with capability of streaming different audio types

slide-21
SLIDE 21

Mar 4, 2009

Audio Interchange Scenarios

Recognition Technologies, Inc. and J. Markowitz Consultants

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

slide-22
SLIDE 22

Mar 4, 2009

Audio Format Header

Recognition Technologies, Inc. and J. Markowitz Consultants

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

slide-23
SLIDE 23

Mar 4, 2009

Audio Interchange Scenarios

Recognition Technologies, Inc. and J. Markowitz Consultants

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

slide-24
SLIDE 24

Mar 4, 2009

22kHz Sampling Rate

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

slide-25
SLIDE 25

Mar 4, 2009

Band Limitation – 8kHz Sampling Rate

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

slide-26
SLIDE 26

Mar 4, 2009

Band Limitation – Telephony (Landline)

Recognition Technologies, Inc.

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

slide-27
SLIDE 27

Mar 4, 2009

Are There any Interchange Requirements Not Covered? Are There any Important Features Missing in General Are There any Formats which will Lose Important Features when Converted?

Conclusion

Recognition Technologies, Inc.

Any other Compelling Reasons to Add more Formats to the Supported List?

A Standard Audio Encapsulation

beigi@RecoTechnologies.com judith@JMarkowitz.com

Please! “Popularity” is no Reason!

slide-28
SLIDE 28

A Standard Audio Encapsulation Method

Homayoon Beigi

Beigi@RecognitionTechnologies.com http://www.RecognitionTechnologies.com

  • f

Recognition Technologies, Inc.

300 Hamilton Avenue White Plains, NY, U.S.A.

Judith Markowitz

Judith@JMarkowitz.com http://www.JMarkowitz.com

  • f
  • J. Markowitz Consultants

5801 N. Sheridan Road Chicago, IL, U.S.A.

and