Speech Separation by Humans and Machines

1. Front Matter

   Pages i-xxiv

   PDF

2. Speech Segregation: Problems and Perspectives

   • Chris Darwin

   Pages 1-4

3. Auditory Scene Analysis

   • Elyse S. Sussman

   Pages 5-12

4. Speech separation

   • Claude Alain

   Pages 13-30

5. Recurrent Timing Nets for F0-based Speaker Separation

   • Peter Cariani

   Pages 31-53

6. Blind Source Separation Using Graphical Models

   • Te-Won Lee

   Pages 55-64

7. Speech Recognizer Based Maximum Likelihood Beamforming

   • Bhiksha Raj, Michael Seltzer, Manuel Jesus Reyes-Gomez

   Pages 65-82

8. Exploiting Redundancy to Construct Listening Systems

   • Paris Smaragdis

   Pages 83-95

9. Automatic Speech Processing by Inference in Generative Models

   • Sam T. Roweis

   Pages 97-133

10. Signal Separation Motivated by Human Auditory Perception: Applications to Automatic Speech Recognition

    • Richard M. Stern

    Pages 135-154

11. Speech Segregation Using an Event-synchronous Auditory Image and STRAIGHT

    • Toshio Irino, Roy D. Patterson, Hideki Kawakhara

    Pages 155-165

12. Underlying Principles of a High-quality Speech Manipulation System STRAIGHT and Its Application to Speech Segregation

    • Hideki Kawahara, Toshio Irino

    Pages 167-180

13. On Ideal Binary Mask As the Computational Goal of Auditory Scene Analysis

    • DeLiang Wang

    Pages 181-197

14. The History and Future of CASA

    • Malcolm Slaney

    Pages 199-211

15. Techniques for Robust Speech Recognition in Noisy and Reverberant Conditions

    • Guy J. Brown, Kalle J. Palomäki

    Pages 213-220

16. Source Separation, Localization, and Comprehension in Humans, Machines, and Human-machine Systems

    • Nat Durlach, Steve Colburn, Gerald Kidd, Chris Mason, Barbara Shinn-Cunningham, Tanya Arborgast et al.

    Pages 221-243

17. The Cancellation Principle in Acoustic Scene Analysis

    • Alain de Cheveigné

    Pages 245-259

18. Informational and Energetic Masking Effects in Multitalker Speech Perception

    • Douglas S. Brungart

    Pages 261-267

19. Masking the Feature Information In Multi-stream Speech-analogue Displays

    • Pierre L. Divenyi

    Pages 269-281

20. Interplay Between Visual and Audio Scene Analysis

    • Ziyou Xiong, Thomas S. Huang

    Pages 283-293

There is a serious problem in the recognition of sounds. It derives from the fact that they do not usually occur in isolation but in an environment in which a number of sound sources (voices, traffic, footsteps, music on the radio, and so on) are active at the same time. When these sounds arrive at the ear of the listener, the complex pressure waves coming from the separate sources add together to produce a single, more complex pressure wave that is the sum of the individual waves. The problem is how to form separate mental descriptions of the component sounds, despite the fact that the “mixture wave” does not directly reveal the waves that have been summed to form it. The name auditory scene analysis (ASA) refers to the process whereby the auditory systems of humans and other animals are able to solve this mixture problem. The process is believed to be quite general, not specific to speech sounds or any other type of sounds, and to exist in many species other than humans. It seems to involve assigning spectral energy to distinct “auditory objects” and “streams” that serve as the mental representations of distinct sound sources in the environment and the patterns that they make as they change over time. How this energy is assigned will affect the perceived n- ber of auditory sources, their perceived timbres, loudnesses, positions in space, and pitches.

• Information
• Neuroscience
• cognition
• computer science
• development
• multimedia
• quality
• science
• speech processing
• speech recognition

• East Bay Institute for Research and Education, USA

  Pierre Divenyi

Policies and ethics