Speechace
  • Introduction
    • Overview
    • Use-Cases
  • Getting Started
    • Pre-requisites
      • API Features
      • Getting the API Key
      • API Regions and endpoints
      • API Limits
    • API Samples
    • Supported Languages
    • API Versioning
    • Authentication
    • Try the Speechace API
    • Error Handling
      • Common Errors
      • Retry Strategies
  • Solutions
    • Speaking Practice for Language Learning
    • Automated Language Assessment with AI
    • Voice AI for Early Literacy
    • Test Prep for Standardized tests
      • PTE Speaking Questions
      • IELTS Speaking Questions
      • TOEFL Speaking Questions
      • CEFR Speaking Questions
      • TOEIC Speaking Questions
    • Speaking Practice in Spanish and French
  • Features
    • Introduction
    • Scripted activities
      • Pronunciation Scoring
        • Word and Sentence pronunciation
        • Multiple choice
        • Custom pronunciations
        • Phoneme list
      • Fluency scoring
        • Passage scoring
      • Lexical stress and intonation
    • Spontaneous activities
      • Open-ended scoring
        • Language scoring
        • Relevance scoring
        • Language detection
      • Task achievement scoring
        • Describe Image
        • Re-tell Lecture
        • Answer Question
  • API Reference
    • Postman API reference
    • Score Text/Pronunciation
      • Handling overall scores
      • Handling word scores
      • Handling phoneme and syllable scores
    • Score Text/Multiple choice
      • Handling multiple choice response
    • Score Text/Markup Language
      • Handling Markup Response
    • Score Text/Stress & Intonation
      • Handing stress and intonation response
    • Score Text/Phoneme list
      • Handling phoneme list response
    • Score Text/Fluency
      • Handling fluency response
      • Fidelity detection
    • Score Text/Validate Text
    • Score Speech/Open-ended
      • Handling language scores
      • Per metric feedback
        • Grammar metrics
        • Vocabulary metrics
        • Coherence metrics
    • Score Speech/Relevance
      • Handling relevance response
    • Score Speech/Language Detection
    • Score Task/Task Achievement
  • Guides on common topics
    • Intepreting quality score
    • Interpreting overall scores
      • Pronunciation Bands
      • Fluency Bands
      • Vocabulary Bands
      • Grammar Bands
      • Coherence Bands
    • Scoring rubrics
    • Interpreting fidelity class
    • Phonetic notation
      • US English (en-us)
      • UK English (en-gb)
      • French (fr-fr, fr-ca)
      • Spanish (es-es, es-mx)
      • US English (en-us)
    • Getting word timestamps in audio
    • Automatic handling of unknown words
    • Phoneme to letter mapping
    • Markup Language
  • Other Resources
    • Requesting Support
    • Rate Limiting
    • Data Retention
    • FAQs
    • Appendices
Powered by GitBook
On this page
  1. Features
  2. Spontaneous activities
  3. Open-ended scoring

Relevance scoring

PreviousLanguage scoringNextLanguage detection

Last updated 7 months ago

Use for scoring the relevance of the response.

The relevance function of the Speechace API is quite unique. While passing an open-ended spontaneous audio file to the Speechace API, developers can also pass in the question prompt provided to the user. The Speechace API's relevance function will then automatically evaluate if the user's response in the audio file is relevant to the question prompt or not. If the response is found to be irrelevant then developers can award a score of 0 to the user's response. This functionality is immensely helpful in building trust with end users as they cannot cheat your spoken language assessment by speaking any random content.

Note that relevance scoring does not require any training on possible answers to a prompt. The AI has been built to identify correct answers for any question automatically.

To illustrate use of the relevance metric, let’s consider an example where two responses to an open-ended question are assessed for relevance.

Example Activity:

  1. Question Prompt: “What are the benefits of learning a new language?”

  2. Probable Responses:

    • Relevant Response: “Learning a new language has numerous benefits. First, it significantly improves communication skills. Being able to converse in another language allows individuals to connect with a wider range of people, fostering better relationships and understanding across cultures. Additionally, it opens up job opportunities. In today’s globalized world, many employers seek candidates who can communicate in multiple languages, as this can enhance business relations and customer service. Overall, the advantages extend beyond personal growth to professional opportunities.”

    • Irrelevant Response: “I like pizza because it’s tasty. There are so many types of pizza, from pepperoni to veggie. My favorite is a Margherita with fresh basil. Pizza is great for parties and gatherings, and it’s so easy to order. Plus, you can customize it however you want, which makes it even better.”

If the user utters a relevant response as above, the developers can create a detailed report that provides the user a positive score as below:

If the user utters an irrelevant response, then based on the , zero score can be assigned to the user and developer's can create a detailed report as shown below to communicate the user's failure:

Such functionality can be built by utilizing the function of the Speechace API.

API
Score Speech/Relevance
Score Speech/Relevance