customer_support · travel · workflow
Airbnb transforms voice support with ML-powered IVR using ASR, intent detection, help article retrieval, and paraphrasing
Airbnb's traditional IVR system relied on rigid menu trees requiring callers to navigate pre-set paths, while generic ASR models produced a word error rate of 33% by misinterpreting Airbnb-specific terminology, undermining downstream intent detection and self-service resolution.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Caller contacts support
IVR picks up and prompts the caller to describe their issue in a few sentences.
Tools used
IVRASRLLM-based ranking modelvector databaseIssue Detection Service
Outcome
The ML-powered IVR reduced ASR word error rate from 33% to approximately 10%, improved customer NPS, reduced reliance on human agents, lowered customer service handling time, improved self-resolution rates, and achieved paraphrasing precision exceeding 90%.
What failed first
Generic pre-trained ASR models misinterpreted Airbnb-specific terms, creating inaccuracies that impacted downstream intent detection and other processes.
Results
Time savedunder 50ms on average
Volumefrom 33% to approximately 10%
Grounding & classification
Source type: technical build writeup
38 fields verified against source quotes.
conversational aiknowledge searchragspeech to textsummarizationvoice aicall recordingknowledge basehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedhospitalitytravelaccuracy improvementcustomer satisfactiondeflection rateresolution time reductiontechnical build writeupcall center aicustomer supportescalation workflowrag answeringvoice call handling