Glossary
Speaker verification
Speaker verification is a voice biometric check in which a system accepts or rejects a claimed identity by comparing a voice with stored models of the person claimed. It is also called voice authentication, voice ID or voice biometrics.
Updated October 17, 20263 cited facts, each traced to its source
Also called voice authentication, voice ID, voice biometrics.
Speaker verification is a check that confirms a voice belongs to the person who claims to be speaking. The person states an identity, and the system accepts or rejects that claim by comparing the voice with stored models for the person claimed. IEEE Technology Navigator puts it directly: in speaker verification, the system accepts or rejects a claimed identity 1.
Verification is a yes or no check
Speaker verification answers one question: is this the person I was told it is? That makes it different from speaker identification, where no identity is claimed. In identification, the system searches a database of known speakers and selects the closest match 2. Verification is a narrower, one-to-one comparison, while identification is one-to-many.
Both are forms of speaker recognition, which IEEE defines as identifying or verifying a person's identity from the characteristics of their voice. Speech recognition, by contrast, asks what was said. Speaker verification asks who said it.
An example: a phone banking line
A caller says "my name is" and gives an account number. The system compares the voice with the model stored for that account. If the match is close enough, the caller is accepted. If not, the caller is sent to a second check or refused. The threshold is set by the company, and a looser threshold accepts more impostors while a stricter one rejects more genuine callers.
The attack to know about: spoofing
A recording of the real person can fool a weak system, and newer text-to-speech tools can synthesize a voice that sounds like the target. IEEE notes that speaker recognition must contend with spoofing attacks, which can include synthesizing speech with text-to-speech tools 3. This is why a voice match alone is a weak password, and why many systems add a second factor, such as a one-time code.
Why it matters for dictation
Dictation software does not verify who you are. It turns speech into text, and a voice match is not needed for that. Voice login and voice ID are separate features, and they depend on a voiceprint, which is stored data that identifies a person. If a product offers voice authentication, read whether the voice model is stored on the device or on a server, and whether you can delete it. The two features should not be confused: a voice profile for dictation settings is not an identity check.
Related terms and guides
Speaker verification uses a voiceprint and falls within biometric data. For the difference between the two kinds of recognition, read voice recognition versus speaker recognition. For the privacy side, see is your voice biometric data? and voice cloning and deepfakes.
Evidence
Every number on this page, with where it comes from. Open a fact to see the exact words in its source.
- 1.
- 2.
- 3.
Related terms
- Speech to Text Privacy: Where Your Voice GoesThe topic this term belongs to
- All-party consentAll-party consent is a recording rule under which every participant in a conversation must agree before it can be recorded or intercepted. California, Florida and Maryland use it in their statutes, and it is stricter than one-party consent.
- Attorney-client privilegeAttorney-client privilege protects confidential communications between a lawyer and their client about seeking legal advice or services. A third party who is present, or a tool that handles the conversation, can put that protection at risk.
- Biometric dataBiometric data is personal data produced by technical processing of a person's physical, physiological or behavioral characteristics that allows or confirms who that person is. A voice recording becomes biometric data when it is processed to identify the speaker.
- Business associate agreement (BAA)A business associate agreement (BAA) is the written contract that HIPAA requires before a covered entity lets a vendor create, receive, maintain or transmit protected health information on its behalf. Dictation tools used in clinics often need one, and a BAA alone does not make a product compliant.
- False accept (accidental activation)A false accept, also called a false wake or accidental activation, is when a voice assistant or dictation feature starts listening or recording although the wake word was not said. Smart speakers have been measured to wake by accident, and that can capture speech the user did not mean to share.
- Federated learningFederated learning is a way to train one machine learning model on data spread across many devices. Each device computes an update from its own data, and only those updates are sent to a server, so the raw data does not have to be collected in one place.
- On-device speech recognitionOn-device speech recognition converts speech to text with a model that runs on your own computer or phone, so the audio does not need to be sent to a server. It is also called local, offline or on-device dictation.
- One-party consentOne-party consent is a recording rule under which a conversation can be recorded lawfully when one of its participants agrees, which is usually the person doing the recording. The US federal wiretap law uses this rule, and individual states may set stricter ones.
- Protected health information (PHI)Protected health information (PHI) is individually identifiable health information that HIPAA protects when it is held or sent in electronic or other form by a covered entity or its business associate. Patient names with diagnoses, in dictated notes or voice recordings, are PHI. It is also called ePHI when held electronically.
- Special category data (GDPR)Special category data is the group of personal data that Article 9 of the GDPR bans organizations from processing unless a listed exception applies. It includes health data and biometric data used to identify a person, and a voice recording can fall into it when it is processed that way.
- Voice cloningVoice cloning is the use of a model trained on recordings of one person to generate new speech in that person's voice. Some products need only minutes of clear audio, and cloned voices have been used in fraud, so recordings of your voice carry a real risk.
- VoiceprintA voiceprint is a stored model of a person's voice, built from measurable features of their speech and used to recognize or verify that person. Illinois law lists voiceprints among biometric identifiers, and other vendors call the same idea a voice template or speaker model.
Pages that use this term
- Speech to Text Privacy: Where Your Voice GoesTopic
- Is Your Voice Biometric Data? GDPR, BIPA and CCPAGuide
- Voice Cloning and Deepfakes: Risks and ProtectionGuide
- Does speech to text collect biometric data?Question
- How does a voice recognition security system work?Question
- Is voice authentication still secure?Question
- What is voice biometrics and how does a voice biometric system work?Question
- Biometric dataGlossary
- Special category data (GDPR)Glossary
- Voice cloningGlossary
- VoiceprintGlossary