DeepAI AI Chat
Log In Sign Up

Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings

10/24/2019
by   Dave Makhervaks, et al.
0

Involvement hot spots have been proposed as a useful concept for meeting analysis and studied off and on for over 15 years. These are regions of meetings that are marked by high participant involvement, as judged by human annotators. However, prior work was either not conducted in a formal machine learning setting, or focused on only a subset of possible meeting features or downstream applications (such as summarization). In this paper we investigate to what extent various acoustic, linguistic and pragmatic aspects of the meetings can help detect hot spots, both in isolation and jointly. In this context, the openSMILE toolkit <cit.> is to used to extract features based on acoustic-prosodic cues, BERT word embeddings <cit.> are used for modeling the lexical content, and a variety of statistics based on the speech activity are used to describe the verbal interaction among participants. In experiments on the annotated ICSI meeting corpus, we find that the lexical modeling part is the most informative, with incremental contributions from interaction and acoustic-prosodic model components.

READ FULL TEXT

page 1

page 2

page 3

page 4

09/30/2017

Confirmation detection in human-agent interaction using non-lexical speech cues

Even if only the acoustic channel is considered, human communication is ...
09/14/2022

Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings

Models of acoustic word embeddings (AWEs) learn to map variable-length s...
04/03/2020

Analyzing autoencoder-based acoustic word embeddings

Recent studies have introduced methods for learning acoustic word embedd...
05/07/2008

Hot Roller Embossing for the Creation of Microfluidic Devices

We report on the hot roller embossing of polymer sheets for the creation...
03/02/2018

Lexico-acoustic Neural-based Models for Dialog Act Classification

Recent works have proposed neural models for dialog act classification i...
04/10/2023

Oh, Jeez! or Uh-huh? A Listener-aware Backchannel Predictor on ASR Transcriptions

This paper presents our latest investigation on modeling backchannel in ...