/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

Study: speech recognition systems from Amazon, Apple, Google, IBM, and Microsoft misidentify words 19% of the time with white people vs. 35% with black people

Technology from Amazon, Apple, Google, IBM and Microsoft misidentified 35 percent of words from people who were black.

New York Times Cade Metz

Discussion

  • @cpayan_ Camilo on x
    @nappy_techie Spanish Siri can't understand my Spanglish, or even English place names lol
  • @nytimesbusiness @nytimesbusiness on x
    Stanford researchers say they have a found a big gap in how well speech-recognition systems understand people who are white and people who are black https://www.nytimes.com/...
  • @_blusummers Brandi T. Summers, Phd on x
    Paging Dr. ⁦@ruha9⁩! “The Stanford study indicated that leading speech recognition systems could be flawed because companies are training the technology on data that is...learning their task mostly from white people, and relatively few black people.” https://www.nytimes.com/...
  • @srchvrs Leonid Boytsov on x
    WOW, in one test of off-the-shelf speech recognition system, the best word error rates were at 20% level and the worse were above 50%. It worked much worse for black folks... yet it does not seem to work really well for white folks either https://www.nytimes.com/...
  • @profjeffries Hasan Kwame Jeffries on x
    “We know the data has bias in it. You don't need to yell that as a new fact. Humans have bias in them, our systems have bias in them. The question is: What do we do about it?"" There Is a Racial Divide in Speech-Recognition Systems, Researchers Say https://www.nytimes.com/...