Jump to Navigation

Main menu

  • Login
Home

Secondary menu

  • [Room Booking]
  • [Wiki]
  • [Webmail]

Samuel J. Yang (Google) - ML meets hearing - Clarity Enhancement Challenge

Date: 
Fri, 05/19/2023 - 10:30am - 12:00pm
Location: 
CCRMA Seminar Room
Event Type: 
Hearing Seminar
What can you do when machine learning meets the ears?  Ears meet ML, ML what can you do for our hearing?

The Clarity Enhancement Challenge is a (successful) attempt to harness machine-learning technology to make our hearing better. The Clarity team provides data and benchmarks, and all of us get to apply our best technology to solve the problem.  In past years they have offered competitions to improve hearing and to measure speech intelligibility.

Sam Yang, Google, was one of the participants in the first challenge, where researchers improved the audibility of a signal in a real room.  Sam will talk about the challenge, the approaches, and the pitfalls of human evaluation.  His approach used DNN speech enhancement in a real situation.  How well does it do?

Who:  Samuel J. Yang (Google)
What:  Machine learning competitions for hearing aids, challenges and opportunities
When:  Friday May 19th at 10:30AM
Where:  CCRMA Seminar Room
Why: A little competition goes a long way, and we all want to hear better.

Bring your favorite ears to CCRMA and we'll talk about how to make them better.


Title: Machine learning competitions for hearing aids, challenges and opportunities

Abstract:
Machine learning-based speech enhancement methods applied to hearing aids and headphones have the potential to significantly impact communication and quality of life for many. Several recent machine learning competitions aim to quantify and facilitate innovation in this area, but not without unexpected difficulties. I'll give an overview of these competitions, and present a deep dive on our entry to the first Clarity Enhancement Challenge where our submission interestingly placed both second and last place.

Biography:
Samuel J. Yang is a Research Scientist at Google Research whose interests lie at the intersection of machine learning, science, and hearing accessibility. He received a MS and PhD in Electrical Engineering from Stanford in 2016, and a BS in Electrical Engineering from Caltech. Samuel is passionate about using machine learning to improve the lives of people with hearing loss.

Paper: https://www.isca-speech.org/archive/pdfs/interspeech_2022/yang22u_interspeech.pdf


Free
Open to the Public
  • Calendar
  • Home
  • News and Events
    • All Events
      • CCRMA Concerts
      • Colloquium Series
      • DSP Seminars
      • Hearing Seminars
      • Guest Lectures
    • Event Calendar
    • Events Mailing List
    • Recent News
  • Academics
    • Courses
    • Current Year Course Schedule
    • Undergraduate
    • Masters
    • PhD Program
    • Visiting Scholar
    • Visiting Student Researcher
    • Workshops 2023
  • Research
    • Publications
      • Authors
      • Keywords
      • STAN-M
      • Max Mathews Portrait
    • Research Groups
    • Software
  • People
    • Faculty and Staff
    • Students
    • Alumni
    • All Users
  • User Guides
    • New Documentation
    • Booking Events
    • Common Areas
    • Rooms
    • System
  • Resources
    • Planet CCRMA
    • MARL
  • Blogs
  • Opportunities
    • CFPs
  • About
    • The Knoll
      • Renovation
    • Directions
    • Contact

Search this site:

Spring Quarter 2023

Music 101 Introduction to Creating Electronic Sounds
Music 128 Stanford Laptop Orchestra (SLOrk)
Music 220C Research Seminar in Computer-Generated Music
Music 250A Physical Interaction Design for Music 
Music 254 Computational Music Analysis
Music 257 Neuroplasticity and Musical Gaming
Music 264 Musical Engagement
Music 319 Research Seminar on Computational Models of Sound Perception
Music 320C Audio DSP Projects in Faust and C++

 

 

 

   

CCRMA
Department of Music
Stanford University
Stanford, CA 94305-8180 USA
tel: (650) 723-4971
fax: (650) 723-8468
info@ccrma.stanford.edu

 
Web Issues: webteam@ccrma

site copyright © 2009 
Stanford University

site design: 
Linnea A. Williams