A collection of Frequently Asked Questions

  • Voice Biometrics topics

  • IngenID One Platform topics

  • General IngenID Policies

Voice Biometrics Topics

Here we answer some of the most common questions about voice biometric technology, terminology, accuracy, and more.

The accuracy of voiceprints is comparable to that of fingerprints and other commonly used biometrics. IngenID regularly tunes production verification systems to 98-99+% accuracy levels, depending on the usage environment and quality of the microphone/device among other factors. IngenID's voice biometric engines use both physiological and behavioral characteristics of your voice to create a unique voiceprint. And since a majority of these characteristics tend to be consistent over time, they can be accurately measured under varying conditions.

Yes. IngenID's voice biometric engines model many different vocal features. Our scoring system models and scores every feature individually and combines them into a composite score. So, if there are small changes to a few features, such as might occur with a cold or allergies, the overall score can still be highly accurate (and the user properly verified).

This is extremely unlikely. A person’s voice is unique to them. And while some professional mimics and comedians might seem to sound like someone else, IngenID voice biometric engines measure and score vocal characteristics that a human being cannot hear (or recreate). Further, many client applications use random prompting techniques to help eliminate prior knowledge of what will be requested. And finally, IngenID has multiple layers of sophisticated anti-spoofing and synthetic speech detection.

In most cases IngenID's audio analysis and filtering tools can handle background noise, allowing IngenID's voice biometric engines to process speech samples without issue. When noise levels are too high however, the IngenID system responds back to the client application so that it can re-prompt the user accordingly. As a general rule, users should be able to speak comfortably from a location with typical noise. Users should avoid loud and noisy areas that are crowded (sporting events, bars, concerts, etc.), as there will be too much audio information for the IngenID system to reliably process.

Yes. People typically have access to several different devices, so it is impractical to require users to only use one. The IngenID platform was designed to accept audio from any application source (IVR system, cell phones, PC or device microphone, etc.). And while it is true that the best results typically occur when a user enrolls and verifies using the same device, IngenID's uses sophisticated channel normalization techniques to address the variations that occur between different audio sources.

IngenID One™ Platform Topics

Here we answer questions about the IngenID One™ Platform, core voice biometric technology, and related items.

Our platform contains a number of different machine learning algorithms, such as GMM, SVM, and i-Vector. And, our platform also contains newer "deep learning" techniques, such as convolutional neural networks, recurrent neural networks, and bi-directional LSTM networks.

Different algorithms are better suited to different use cases, and also depend on how much training data is available to tune the system. IngenID works with our clients and partners to configure our platform with the optimal algorithm(s) for their particular circumstances.

A mix of both. IngenID has its own team of voice biometric engineers, system architects, researchers, and developers -- so we do develop our own technology. However, we also have an exclusive, worldwide license to key deep learning technology developed at the University of Rochester.

The IngenID One™ Platform supports standard WAV audio files with headers. Acceptable forms include: PCM, u-Law, and a-Law. Your audio files should be mono (single channel) and only include speech from one speaker. Files can be 8-bit or 16-bit and 16kHz, but we recommend 16-bit, 16kHz for new clients.

NOTE: the majority of available speech information can be determined from 16-bit, 16kHz samples, so anything more than this will not really buy you much in the way of accuracy. Hence, we do not accept higher resolution files.

Personal Data Protection Topics

Here we answer questions regarding how we protect Personal Data.

IngenID takes the collection of personally identifiable information (PII) very seriously. We only collect speech samples (source WAV audio or media streams) which we use to process into voiceprints, or to compare to stored voiceprints during verify and identify requests.

For clients using our optional Automatic Speech Recognition (ASR) features, we may also collect content descriptions for the speech samples that are sent to us. And, if our clients and partners are using an IngenID partner's integrated IVR system, the use of outbound calling requires that telephone numbers be sent to us.

Personal Data can only be sent to the system via IngenID's secure APIs, which require an account code and API access token. We further require all clients and partners to use HTTPS to transmit data to us using TLS 1.2. Once data is received in the IngenID platform, it is either discarded from memory or written to our secure database. Any Personal Data that is stored in IngenID's database is encrypted using AES-256 encryption under FIPS 140-2 guidance.

IngenID Policies and Related Topics

Here we answer a variety of questions about doing business with IngenID, our policies, etc.

IngenID does not currently have a formal partner program. However, we do have many partners globally and have many of the expected components of a partner program, such as: partner pricing discounts, partner resale agreements, partner technology training and support documentation, marketing support documents, meeting preparation and presentation assistance, etc.

The most successful IngenID partners actively use our technology, either to develop custom applications for their clients, or to embed and host within their own products and services, or to combine with their own products and services for resale. If you're interested in partnering with IngenID, please Contact Us.

NOTE: IngenID does NOT allow any pure resale partners.

Clients using IngenID's data center can choose from several different subscription plans, supporting volumes up to 2MM transactions per month. If volume requirements exceed 2MM transactions per month, IngenID may require private instances to be set up. It's important to note that IngenID offers volume discounts; the higher the monthly transaction volume commitment, the lower the per-transaction price.

Clients choosing to deploy the IngenID in their own data center can choose between our subscription plans or a "hybrid" plan. Hybrid plans are subscription-like, with monthly fees. However, are also license-like, as they are based on functionality used and come with unlimited users and unlimited usage per user.

Yes. We have numerous hard-iron and virtualized instances of the IngenID One™ Platform located in the private data centers of our clients and partners. Or if you prefer a public cloud, we have deployments in Alibaba Cloud, Amazon AWS, Google Cloud, IBM Cloud, and Microsoft Azure.

Yes. IngenID does not have its own IVR system either. Instead, we've built plug-ins to support numerous IVR platforms. Thus, clients can directly incorporate standard enrollment and verification dialogs into their applications without the need for any IVR programming. Just setup an account in Twilio or Aspect for instance (we support others too), fill in the plug-in form fields, and you'll be up and running in minutes.

It is also important to note that the IngenID One™ Platform can accept audio from almost any source. We have clients providing us with audio from IVR systems, call centers, mobile applications, WebRTC, Bluetooth speakers, traditional microphones, medical devices, and IoT devices. As long as you can provide speech samples to us via one of our supported audio file formats (or streaming), we should be able to process voice biometric requests for you!

Due to IngenID's comprehensive security protocols, it is extremely unlikely that any voiceprint will ever be stolen or hijacked. However, if a voiceprint were to find its way outside of the IngenID One™ Platform, absolutely nothing would happen! There are a couple important reasons why.

First, IngenID's voiceprints are essentially mathematical models of how a person speaks. They are not files that can be played or turned into intelligible speech. Plus, IngenID uses a proprietary storage format, so only IngenID's system can interpret and use them. And second, voice biometric systems work by submitting speech samples to them, extracting features, and then comparing these extracted features to a reference voiceprint. Simply put, a voiceprint cannot be submitted directly to IngenID's system, nor to any competitor's system.