Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Intro to Speech recognition - AI Facebook Devc ...

Intro to Speech recognition - AI Facebook Devc Nairobi Master class

The speech recognition aims at understanding
and comprehending WHAT was spoken.
It is used in hand-free computing, map, or menu navigation.
Different from Voice recognition (It is used to identify a person by analyzing its tone, voice pitch, and accent)

Avatar for Ir Nahayo Ndindayino

Ir Nahayo Ndindayino

October 07, 2017
Tweet

More Decks by Ir Nahayo Ndindayino

Other Decks in Education

Transcript

  1. 2 Intro • The speech recognition aims at understanding and

    comprehending WHAT was spoken. • It is used in hand-free computing, map, or menu navigation. • Diferent from Voice recognition (It is used to identify a person by analyzing its tone, voice pitch, and accent)
  2. 3 Concepts • Agents: agents are applications. We create an

    agent as a means of grouping individual entities and intents. • Entities – entities are custom concepts that we want to incorporate into our application. They provide a way of giving meaning to a specifc concept by means of adding examples. A sample entity would be ‘currency’. We defne it by adding synonyms such as ‘USD’, ‘US Dollar’, or just ‘Dollars’. Each synonym is then assigned to a reference value that can be used in the code.
  3. 4 Concepts (Ctd.) • Intents – intents allow us to

    defne which actions the program will execute depending on what a user says. A sample intent would be ‘convert currency’ • Contexts – contexts represent the current context of a user expression.
  4. 5 Why Speech Recognition is so Difficult Intra-speaker variability Noise/reverberation

    Coarticulation Context-dependency Word confusability Word variations Speaker Dependency Multiple Interpretations Limited vocabulary Ellipses and Anaphors