Speech technology products One recording button
brings thousands of
options to life
OUR TECHNOLOGIES
Pronunciation assessment

Pronunciation assessment

The quality of the pronunciation of the responses is assessed real-time. The student gets a score expressed as a percentage, that represents the extent to which the pronunciation corresponds to the pronunciation of a native speaker. Besides the student gets feedback on the quality of each separate phoneme. Both the score and feedback can be tailored to the personal language level of the student.

Prices

Per user/ year
€0.86
  • Scores available on PHONEME WORD, SENTENCE LVL
  • Automatic conversion FROM TEXT TO SOUND
  • Cloud infrastructure designed FOR REAL-TIME ASSESSMENT
  • Assessment of sound AND OF FLUENCY

Speech recording

Streaming speech recording, high quality audio recording to the Cloud. Via a unique link audio files can be retrieved from and shared with any internet enabled device.

Prices

Per user/ year
€0.28

SEE THE DEMO

Speech recording
  • Storage of uncompressed HIGH-QUALITY SOUNDS IN CLOUD
  • Instant listen back AND AUDIO RETRIEVAL THROUGH A LINK
  • Browser-based components FOR DESKTOP AND MOBILE
  • Secure authentication AND ADVANCED VIA REST API
Speech Recognition

Speech Recognition

Our speech recognition converts audio into text, we optimized this technology for English language learners. It enables students to respond by voice to stimulate speaking instead of only using the keyboard or mouse.

Prices

Per user/ year
€0.49
  • Speech Recognition FOR FAST RECOGNITION
  • Streaming technology FOR FAST RESPONSES
  • Suitable for speech OF CHILDREN AND ADULTS
  • Supported language ENGLISH (DUTCH IS COMING)
Speech annotation tool

Speech annotation tool

Speech recordings can be played back and annotated. It’s a very handy tool for scoring speech from students or clients that need to be analysed for reading mistakes. Specific error labels can be assigned to parts of the audio. The results can be used for further investigation by a more senior annotator, or simply be archived for a longer time.

It’s useful as a standalone tool for individual linguists and speech therapists. It also serves as a hub for annotating massive amounts of speech recordings, for assignment to multiple annotators. Here, the goal is teaching the machine learning algorithms how to detect reading errors automatically. The tool is previously used to train our speech models for English and Dutch.

The tool can be tailored to suit the needs of our customers (different target languages, different error labels) to optimize trained models for your target audience.

Prices

Demo and pricing information available upon request. Usually part of a R&D arrangement.
  • Forced alignment maps speech to prompt
  • Batch processing assign audio batches to multiple annotators
  • High consistency through inter annotator agreement
  • Customisable labels extract features you care about

Loudly

Loudly is a serious game with speech technology to learn vocabulary and is specially developed for schools and their students. The students practice their vocabulary, spelling and pronunciation and do self-assessments.

Scientific research with an English learning app

Loudly is a didactical concept to learn vocabulary by using speech technology. Students will efficiently improve not only their vocabulary and their spelling but also their pronunciation. Unique is the option to assess their own pronunciation by comparing it with the pronunciation of a native speaker.

Scientific research proves that to make oneself understood, good pronunciation is more effective than good grammar. And that an adequate pronunciation has a positive impact on listening, writing and reading skills. Students who are in for some challenge can use the competition modus, where they can challenge themselves or fellow students and aim for the highest score.

Loudly website

Loudly

Benefits

  • Years of scientific research by the
    University of Sheffield is available in
    an easy to use API

  • Implementation examples for pronunciation
    assessment exercises are available. Source
    code is open source and available
    via Github

  • Experienced team and proven
    process to validate the automatic
    assessment to assure quality

  • Flexibility to implement custom user
    interaction and feedback mechanisms
    tailored to specific user groups

  • Professional research and
    a development team that is qualified to
    include more (sub)competences
    for automatic assessment

  • Privacy and processing of personal
    data in line with policy trade
    an organization of publishers, a.o data
    storage on European territory

Implementation

The Javascript SDK for the ITSLanguage speech recognition is open source
and available on Github. Meet our software development team for a quick walkthrough.
Basic implementation will take two days. Trial and commercial API keys are available.

Browse to Github

Implementation
  • Browser-based all HTML and no Flash
  • JS SDK and reference implementation
  • Secure authentication and advanced via REST API
  • Scalable to millions of users
Close video