System for automatic extraction of structure from spoken conversation using lexical and acoustic features

US10592611B2 · kind B2 · utility

Assignee

• Conduent Business Services, LLC · US

Inventors

• Jesse Vig · Los Altos, US
• Harish Arsikere · Bengaluru, IN
• Margaret H. Szymanski · Santa Clara, US
• Luke Plurkowski · Antioch, US
• Kyle D. Dent · San Carlos, US
• Daniel G. Bobrow · Palo Alto, US
• Daniel Davies · Elizabeth, US
• Eric Saund · Redwood City, US

Key dates

• Filing date: Oct 24, 2016
• Grant date: Mar 17, 2020
• Expiry date: Jan 20, 2037

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04M2203/357
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Embodiments of the present invention provide a system for automatically extracting conversational structure from a voice record based on lexical and acoustic features. The system also aggregates business-relevant statistics and entities from a collection of spoken conversations. The system may infer a coarse-level conversational structure based on fine-level activities identified from extracted acoustic features. The system improves significantly over previous systems by extracting structure based on lexical and acoustic features. This enables extracting conversational structure on a larger scale and finer level of detail than previous systems, and can feed an analytics and business intelligence platform, e.g. for customer service phone calls. During operation, the system obtains a voice record. The system then extracts a lexical feature using automatic speech recognition (ASR). The system extracts an acoustic feature. The system then determines, via machine learning and based on the extracted lexical and acoustic features, a coarse-level structure of the conversation.