Events

Program

2019 AES International Conference on Audio Forensics

Details  /  Registration  /  Program

Special Sessions  /  Sponsors

Venue & Accommodations  /  Social Event  / News & Updates

 

Audio forensics conference

 

Original Call for Contributions (closed)

Tuesday, June 18

9:00 - 10:00

Keynote 1: "Lossy compression in digital evidence: Easier or more difficult?" Karlheinz Brandenburg

10:00 - 10:40

Paper Session 1: GUNSHOT ANALYSIS 1

-      Overview of Forensic Audio Gunshot Analysis Techniques (Begault, et al)

-      A Short-Time Cross Correlation with Application to Forensic Gunshot Analysis (Beck)

10:45 - 11:15

Coffee Break

11:15 - 12:15

Paper Session 2: GUNSHOT ANALYSIS 2

-      Shot-to-shot variation in gunshot acoustics experiments (Maher)

-      Who Fired When: Associating Multiple Audio Events from Uncalibrated Receivers (Beck)

-      Improved gunshot classification by using artificial data (Busse, et al)

12:30 - 14:00

Lunch

 

14:00 - 15:00

Tutorial 1: AUTHENTICATION Catalin Grigoras

15:00 - 15:40

Paper Session 3: AUTHENTICATION 1

-      Inverse decoding of PCM A-law and µ-law (Cuccovillo & Aichroth)

-      Copy-Move Forgery Detection and Localization via Partial Audio Matching (Maksimović, et al)

15:45 - 16:15

Coffee Break

16:15 - 17:15

Paper Session 4: AUTHENTICATION 2

-      Forensic Authenticity Analyses of the Metadata in Re-Encoded M4A iPhone iOS 12.1.2 Voice Memos Files (Koenig & Lacey)

-      Detection of In-App Apple Voice Memo Edits through Interpolation Artefacts (Zjalic)

-      Forensic Analysis of AAC Encoding on Apple iPhone Voice Memo Recordings (Grigoras & Smith)

17:30

Cocktail Reception


Wednesday, June 19

9:00 - 10:00

Keynote 2: "Source-Filter Processing for Audio Forensics" Udo Zölzer

10:00 - 10:40

Paper Session 5: SPEAKER RECOGNITION/ANALYSIS 1

-      Premature Overspecialization in Emotion Recognition Systems (Assunção, et al)

-      Fighting AI with AI: Fake Speech Detection using Deep Learning (Malik & Changalvala)

10:45 - 11:15

Coffee Break

11:15 - 12:15

Platinum talks

- Narrowing the gap between live surveillance and the forensic laboratory (Gordon Reid, CEDAR)
- The who, the when and the what - challenges in the development of real-world solutions for forensic audio processing (Anil Alexander, Oxford Wave Research)

12:30 - 14:00

Lunch


14:00 - 15:00

Tutorial 2: AUTOMATIC SPEAKER RECOGNITION Eliud Bonilla

15:00 - 15:40

Paper Session 6: SPEAKER RECOGNITION/ANALYSIS 2

-      Deep neural network based forensic automatic speaker recognition in VOCALISE using x-vectors (Kelly, et al)

-      Phonetic-oriented identification of twin speakers using 4-second vowel sounds and a combination of a shift-invariant phase feature (NRD), MFCCs and F0 information (Ferreira)

15:45 - 16:15

Coffee Break

16:15 - 17:15

Workshop 1: GUNSHOT ANALYSIS Begault, Maher, Beck

17:30

Social Event departure


Thursday, June 20

9:00 - 10:00

Tutorial 3: DEEP LEARNING FOR AUDIO Andy Sarroff

10:00 - 10:40

Paper Session 7: SCENE/MICROPHONE CLASSIFICATION & STEGANOGRAPHY 1

-      Bag-of-Features Models Based on C-DNN Network for Acoustic Scene Classification (Pham, et al)

-      Beyond Equal-Length Snippets: How Long is Sufficient to Recognize an Audio Scene? (Phan, et al)

10:45 - 11:15

Coffee Break

11:15 - 12:15

Paper Session 8: SCENE/MICROPHONE CLASSIFICATION & STEGANOGRAPHY 2

-      Exploiting Frequency Response for the Identification of Microphone Using Artificial Neural Networks (Hafeez, et al)

-      Directivity and Sensitivity of Cell Phones: iPhone 7 (Brixen)

-      Steganography for Indoor Location (Moutinho, et al)

12:15 – 14:00

Conference closure and Lunch

 

Platinum Sponsors:

CEDAR Audio Ltd.   Oxford Wave Research

 

 

Institutional Sponsors:

FEUP   APEA   ATP   ATP

 

AES - Audio Engineering Society