Custom display post processing in speech recognition

US12061861B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Wei-Min Liu · Dublin, US
• Padma Varadharajan · Palo Alto, US
• Piyush BEHRE · Santa Clara, US
• Nicholas Kibre · Redwood City, US
• Edward C. Lin · Beijing, CN
• Shuangyu Chang · Fremont, US
• Che ZHAO · Beijing, CN
• Khuram Shahid · Seattle, US
• Heiko Rahmel · Bellevue, US

Key dates

• Filing date: Jul 26, 2022
• Grant date: Aug 13, 2024
• Expiry date: Jul 26, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G10L15/26
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.