Using the Speechace API as Voice AI for kids

by Speechace 9 months ago

Can you use Speechace with kids? We get this question often and the answer is Yes. Speechace can serve as a Voice AI for kids eLearning activities.

Last week the surprise sale of Soapbox Labs sent a flurry of eLearning providers looking for alternatives to the Soapbox Labs API. In this post we will share some details on how the Speechace API can be used as a Voice AI for kids platform and as a replacement for Soapbox Labs.

tldr

Yes the Speechace API can be and has been widely used in K-12 activities for kids (like in this social robot built by MIT Media lab). While the Speechace models are general and not exclusively kids trained, our models are large and broad in nature and perform well with kids from Kindergarten age and up in both early literacy and second language learning contexts.

In fact, the Speechace API is in use by several large K-12 Education Publishers and eLearning providers in countries such as: Brazil, India, Germany, Vietnam, the United States, and many others.

Speechace can be used to support a variety of kids Voice AI use cases (more on these below):

  • Phonics Reading
  • Sight words
  • Voice-based MCQ
  • Oral Reading Fluency (ORF)
  • English Language Learning (ELL)

Does Speechace offer specific or custom models for kids?

We serve our K-12 use cases from the same general model. Speechace has always been open to the idea of custom or use case specific models, but first we start by testing how well such requirements can be addressed by the general model. So far, the general model has performed well for kids use cases. And just as important, progressive new versions of the general model demonstrated improvement in accuracy for kids use cases.

The advantage of a general model is that it generalizes better to address a variety of use cases and demographics, and is less prone to over-fitting. It also allows Speechace to move faster continuously investing in and releasing improvements which benefit all use cases. Our general model is on its 9th major generation. Our most recent update involved a 10x acoustic model size upgrade and a major re-architecture to take advantage of new GPU capabilities. This yields accuracy and performance gains which become instantly available to all customers and use cases.

How well does Speechace work on kids?

Let’s talk metrics. First, let’s qualify the dataset we will report metrics on. It’s easy to show great looking results on a small trivial dataset, thin on pronunciation errors, recorded under pristine conditions by mostly native speakers. The real world, of course, is anything but that.
 
Our dataset is:
  • Over 5000 items in size
  • Recorded from over 350 different child speakers
  • Is balanced in terms of Label 1 (Correct) items and Label 0 (Incorrect) items
  • Comes from a real world production environment with noise, background talk, insertions, repetitions, interruptions and everything you might expect when a young child does their homework with family, siblings and life happening around them.
  • Contains long and short utterances and is not just single words
  • A holdout dataset never seen or used in training

Results:

On this challenging dataset, Speechace is 86% accurate across the set, outperforming a well-known rival API. Speechace performs well identifying both Label 0 (Incorrect) words and Label 1 (Correct) words with an F1 Score of 0.87 and 0.84 respectively yielding an overall F1 score of 0.86.

What kind of Kids speaking activities can you build with Speechace?

1. Phonics Reading

With the phonics reading, early literacy learners practice sounding out letters and reading words while receiving immediate feedback on their pronunciation.

Try a sample phonics reading activity or head to the API Docs to see an example of using markup language to code a phonics reading example. With markup language you have complete flexibility to markup:

  • Letter names and letter sounds
  • Made-up words
  • Present feedback by color coding letters

2. SIGHT WORDS

Sight words allow kids to practice recognizing and speaking common words, which is important for building a strong foundation in reading and writing.

Try a sample word pronunciation activity or check the API Docs for an example word pronunciation API request.

You can color code words for intuitive feedback by interpreting the word quality score. You can also color code individual letters in the word and not expose the notion of phonetic notation to early learners.

 

3. Voice-based MCQ

Voice-based multiple choice questions enable game-like engaging learning activities for kids. With this feature, kids can answer questions using their voice, making the experience more interactive and fun.

Try a speak the right answer activity or check the API Docs for an example Score a Multiple Choice Text request.

Tired of coming up with lists of multiple choice distractors?

Try our new Score Task API and let our integrated LLM automatically identify correct answer(s) based on a provided context.

4. Oral Reading Fluency (ORF)

Oral reading fluency (ORF) is another key feature of the Speechace API for kids. This allows kids to record themselves reading a passage aloud and receive feedback on their reading pace, accuracy, and fluency. This is important for developing confident and independent readers.

Try a fluency activity or check the API Docs for an example Score Fluency request.

With the API response you can:

  • Report Word Correct Per Minute (WCPM)
  • Highlight word errors, insertions, and omissions
  • Indicate incorrect pauses, hesitations, and fillers

Conclusion

In conclusion, the Speechace API can be a great tool for building Voice AI for kids solutions from Kindergarten age and up. It has been widely used by K-12 education publishers and eLearning providers around the world and has been proven to be effective in various use cases such as phonics reading, sight words, oral reading fluency, and English language learning.

Despite being a general model, it has performed exceptionally well in addressing the specific needs of kids. With continuous updates and improvements, the Speechace API offers a versatile and reliable platform for creating engaging and interactive voice-based activities for kids. 

If you’d like us to show you how Speechace can help address your needs send a note at contact@speechace.com

You can find all the necessary resources to start with the Speechace API at https://docs.speechace.com

All the best,

The Speechace Team