Mobirise


Democratizing voice computing

Reduce the time to collect, model, and monetize voice data from years to minutes!

Our Products

We're building a portfolio of technologies to power voice-enabled devices.

Mobirise

SurveyLex

The world's first voice-enabled survey platform. Collect voice samples across any device through web browsers.

Mobirise

NeuroLex API

Use our API to clean, featurize, and model voice files. Get charged per-minute of audio processed.

Our Services

We can work alongside your team to unleash the power of voice computing.

Mobirise

Data collection

Use our SurveyLex product to collect massive datasets through web browsers.

Mobirise

Data cleaning 

Remove noise or augment voice datasets to be indicative of real-world use.

Mobirise

Featurization

We can extract state-of-the art feature embeddings for audio, text, and image data.

Mobirise

Machine learning

Work with our team to build deep learning models from your voice data.

Mobirise

Speaker diarization

Work with our team to source-separate multiple speakers.

Mobirise

Data labeling

Use our team to manually or automatically label datasets. 

Mobirise

Monetization

Work with our team to find new ways to monetize your voice data.

Mobirise

Server deployments

Use our API to clean, featurize, and model voice data on servers.

Datasets

We're curating the best voice datasets in the world.

Mobirise

Voicemails

Over 150,000 unique voicemails and speakers leaving messages around anniversaries and birthdays.

Mobirise

Emotions

3,000+ labels of each emotion type: happy, sad, disgust, angry, fear, surprise, and neutral.

Mobirise

Accents

1,000+ samples in 16 types of English accents all repeating the same sentence. 

Mobirise

Genders

10,000+ gender labels (e.g. male or female) across many accents. 

Mobirise

Microphone type

>1000 voice samples in each class: iPhone and/or iMac computer.

Mobirise

Speaking type

1,000+ samples of users speaking naturally or abnormally (e.g. singing).

Mobirise

General computer use

5,000+ samples labeled as voice events, music events, typing events, and silence events. 

Mobirise

Fatigue

1,000+ samples labeled with fatigue level (e.g. awake or tired).

Mobirise

Depression

500+ voice data samples with self-reported PHQ-9 scores, a measure for depression.

Mobirise

Schizophrenia

300+ voice data samples with self-reported BPRS scores, a measure for psychosis.

Mobirise

Parkinson's disease

2,000+ patients labeled with Parkinson's disease with a short voice utterance ('ahhh').

Mobirise

Alzheimer's disease

200+ patients with MRI images labeled with mild-cognitive impairment vs. controls.

Our Process

Start your free 14-day trial today.

Mobirise

Step 1:
Discovery Call ➡

Schedule a call to discuss how we can add value to your organization through a subscription, data license, or a service contract.

Mobirise

Step 2:
Strategic plan ➡

We then write up a short strategic plan with a mission, goals, and success metrics for a risk-free 14-day trial trial.

Mobirise

Step 3:
Trial period ➡

We then move forward with this free 14-day trial to test the subscription, data license, or service contract on the defined success metrics.

Mobirise

Step 4:
Contract signing

We can then move forward with an engagement. Typically, engagements occur over 3, 6, 12, or 18 months.

Trusted by...

In the Press

Frequently Asked Questions

We recently wrote a textbook to help train more developers in this field.

Check it out at this link.

Yes! We can customize service contracts to meet your needs. Here are some services that we can provide beyond our core product offerings:

1.  Manual data labeling - $1/minute of audio per label
2. Automated data labeling - $0.12/minute of audio
3. Data cleaning - $100/hour
4. Data modeling - $150/hour
5. Research assistants (collect data) - $15/hour
6. Speaker diarization (up to 3 speakers) - $0.024/minute of audio processed
7. Hardware design - Varies based on scope
8. Manual transcription (100% accuracy) - $0.80/minute
9. Amazon Alexa skills / Google Assistant apps - $1,000/application
10. Custom software development - Varies based on scope 

If you want something done that does not fit the above list, reach out to us. We most likley are able to help you with the >30 voice engineers in our lab.

We can start projects immediately and scale-up very quickly.

Just book a meeting on our calendar here and we'll handle the rest. 

We commonly get asked how many and what types of features we extract to build machine learning models. Simply, there are 4 main types of features that we can extract:

1. Audio features - acoustic features extracted from an audio file (e.g. fundamental frequency)

2. Text features - language features extracted from a transcript (e.g. noun frequency)

3. Mixed features - Mixing up audio features and text features - often as a ratio (e.g. speaking rate).

4. Meta features - features derived from machine learning models on any of the embeddings described above (e.g. age - 20s).

You can read more about each of these types of features in this SurveyLex FAQ document.

We have an internal product, ModLex, which makes it quite easy for us to featurize and optimize machine learning models automatically. This makes it much more affordable for you to build machine learning models at a low cost.

Right now we’re training mostly simple classification models because many of the datasets that we have curated internally are relatively low sample sizes (e.g. 100-1000 labels per class). However, for larger datasets we build and optimize models with deep learning techniques (e.g. attention-based neural networks). Here is a list of all the model families that we test currently with the ModLex software:

- Naive Bayes (NB)
- Decision tree
- Support vector machines (SVM)
- Bernoulli
- Maximum entropy
- Adaboost
- Gradient boost
- Logistic regression
- Hard voting
- K nearest neighbors (knn)
- Random forest

After running the ModLex software with one of the training scripts, we can then assess it’s accuracy in the form of a .TXT file output. This process allows us to rapidly prototype many different feature embeddings and model types at once.

We originally started NeuroLex to diagnose psychiatric and neurological conditions through voice biomarker screening tests.

You can learn more about NeuroLex's story here.

Contact us

How can we work together?

© Copyright 2018 NeuroLex Laboratories, Inc