Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Barista: A Framework for Concurrent Speech Processing by USC-SAIL.

Doğan Can1, James Gibson1, Colin Vaz1

  • 1Signal Analysis and Interpretation Lab, University of Southern California, CA 90089.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)
|September 10, 2016
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Marine sulfated glycan inhibits tau-heparan sulfate interaction and tau cellular uptake.

International journal of biological macromolecules·2026
Same author

An Expectation Maximization approach to Joint Modeling of Multidimensional Ratings derived from Multiple Annotators.

Interspeech·2026
Same author

N-Sulfated Heparan Sulfate Promotes Reelin Signaling as a Co-receptor.

Journal of the American Chemical Society·2025
Same author

Developing personalized algorithms for sensing mental health symptoms in daily life.

Npj mental health research·2025
Same author

Insights into nanoparticle surface bonding and coating architecture via multinuclear NMR.

Academia nano : science, materials, technology·2025
Same author

An Evaluation of the Microsoft HoloLens2 in the Clinical Teaching of Pain Pathways for Undergraduate Medical Students.

The journal of education in perioperative medicine : JEPM·2025
Same journal

MAP Image Recovery with Guarantees using Locally Convex Multi-Scale Energy (LC-MUSE) Model.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)·2026
Same journal

EARLY DETECTION OF COGNITIVE DECLINE USING VOICE ASSISTANT COMMANDS.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)·2025
Same journal

CROSS-DOMAIN DIFFUSION BASED SPEECH ENHANCEMENT FOR VERY NOISY SPEECH.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)·2025
Same journal

CROSS-DOMAIN SPEECH ENHANCEMENT WITH A NEURAL CASCADE ARCHITECTURE.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)·2025
Same journal

ESTIMATING DIRECTED SPECTRAL INFORMATION FLOW BETWEEN MULTI-RESOLUTION TIME SERIES.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)·2025
Same journal

NEURAL CASCADE ARCHITECTURE FOR JOINT ACOUSTIC ECHO AND NOISE SUPPRESSION.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)·2025
See all related articles

Barista is an open-source framework for concurrent speech processing. It enables customizable, distributed speech recognition and training workflows on parallel hardware.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Speech Processing

Background:

  • Concurrent and distributed systems are crucial for handling complex speech processing tasks.
  • Existing toolkits may lack flexibility or ease of use for custom network construction.

Purpose of the Study:

  • Introduce Barista, an open-source framework for concurrent speech processing.
  • Provide an extensible and user-friendly platform for building customizable speech processing networks.

Main Methods:

  • Developed Barista based on the Kaldi speech recognition toolkit and the libcppa actor library.
  • Modeled Barista networks on data flow between simple actors communicating via message passing.
  • Utilized libcppa for efficient concurrency and distribution mechanisms.
Keywords:
C++actor modelconcurrency and distributionopen sourcereal-time speech recognition

Related Experiment Videos

Main Results:

  • Barista facilitates the creation of highly customizable concurrent and/or distributed speech processing networks.
  • Enables demanding tasks like real-time speech recognition and complex training workflows.
  • Supports scheduling and execution on parallel and/or distributed hardware.

Conclusions:

  • Barista offers an accessible and extensible solution for advanced speech processing.
  • The framework supports efficient execution of complex tasks on parallel infrastructure.
  • Released under the Apache License v2.0 for broad adoption.