Systems and methods for training voice query models
US12094452B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 22, 2021 |
| Grant date | Sep 17, 2024 |
| Priority date | — |
| Expiry date | Nov 23, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0638
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods for automatically evaluating ASR outputs and providing annotations, including corrections, on the transcriptions—in order to improve recognition—may be based on an analysis of sessions of user voice queries, utilizing time-ordered ASR transcriptions of user voice queries (i.e., user utterances). This utterance-based approach may involve extracting both session-level and query-level characteristics from a voice query sessions and identifying patterns of query reformulation in order to detect erroneous transcriptions and automatically determine an appropriate correction. Alternative, or in addition, ASR outputs may be evaluated based on user behavior. The outcomes may be classified as positive or negative. An ASR transcription may be labeled using the description of the outcome. The labeled transcription may be used as training data to train a model to output improved transcriptions of voice queries.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.