FraudDetectionResult - Amazon Connect Voice ID

FraudDetectionResult

Contains information produced as a result of performing fraud detection on a speaker.

Contents

AudioAggregationEndedAt

A timestamp indicating when audio aggregation ended for this fraud detection result.

Type: Timestamp

Required: No

AudioAggregationStartedAt

A timestamp indicating when audio aggregation started for this fraud detection result.

Type: Timestamp

Required: No

Configuration

The FraudDetectionConfiguration used to generate this fraud detection result.

Type: FraudDetectionConfiguration object

Required: No

Decision

The decision produced by VoiceID as a result of the fraud detection process.

Type: String

Valid Values: HIGH_RISK | LOW_RISK | NOT_ENOUGH_SPEECH

Required: No

FraudDetectionResultId

The unique identifier for this fraud detection result. Given there can be multiple fraud detections for a given session, this field helps in identifying if the returned result is from previous streaming activity or a new result. Note that in the absence of any new streaming activity or risk threshold changes, VoiceId always returns cached results for this API.

Type: String

Length Constraints: Fixed length of 22.

Pattern: ^[a-zA-Z0-9]{22}$

Required: No

Reasons

The reason a speaker is identified as a fraudster. There is currently only one valied value, KNOWN_FRAUDSTER, and is only populated if the fraud detection reason is HIGH_RISK.

Type: Array of strings

Array Members: Minimum number of 0 items. Maximum number of 3 items.

Valid Values: KNOWN_FRAUDSTER

Required: No

RiskDetails

Details about each risk analyzed for this speaker. Currently, this contains KnownFraudsterRisk details.

Type: FraudRiskDetails object

Required: No

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: