Name
Title | ||
|---|---|---|
Toward automating a human behavioral coding system for married couples' interactions using speech acoustic features |
Abstract | ||
|---|---|---|
Observational methods are fundamental to the study of human behavior in the behavioral sciences. For example, in the context of research on intimate relationships, psychologists' hypotheses are often empirically tested by video recording interactions of couples and manually coding relevant behaviors using standardized coding systems. This coding process can be time-consuming, and the resulting coded data may have a high degree of variability because of a number of factors (e.g., inter-evaluator differences). These challenges provide an opportunity to employ engineering methods to aid in automatically coding human behavioral data. In this work, we analyzed a large corpus of married couples' problem-solving interactions. Each spouse was manually coded with multiple session-level behavioral observations (e.g., level of blame toward other spouse), and we used acoustic speech features to automatically classify extreme instances for six selected codes (e.g., ''low'' vs. ''high'' blame). Specifically, we extracted prosodic, spectral, and voice quality features to capture global acoustic properties for each spouse and trained gender-specific and gender-independent classifiers. The best overall automatic system correctly classified 74.1% of the instances, an improvement of 3.95% absolute (5.63% relative) over our previously reported best results. We compare performance for the various factors: across codes, gender, classifier type, and feature type. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1016/j.specom.2011.12.003 | Speech Communication |
Keywords | Field | DocType |
human behavioral coding system,feature type,coding process,behavioral science,standardized coding system,best result,speech acoustic feature,global acoustic property,married couple,acoustic speech feature,multiple session-level behavioral observation,human behavioral data,classifier type,prosody | Prosody,Spouse,Computer science,Blame,Observational methods in psychology,Coding (social sciences),Speech recognition,Behavioural sciences,Classifier (linguistics),Dyadic interaction | Journal |
Volume | Issue | ISSN |
55 | 1 | 0167-6393 |
Citations | PageRank | References |
30 | 1.21 | 30 |
Authors | ||
8 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Matthew P. Black | 1 | 192 | 13.67 |
| Athanasios Katsamanis | 2 | 301 | 22.71 |
| Brian R. Baucom | 3 | 152 | 16.36 |
| Chi-Chun Lee | 4 | 654 | 49.41 |
| Adam C. Lammert | 5 | 92 | 8.35 |
| Andrew Christensen | 6 | 52 | 2.29 |
| Georgiou Panayiotis | 7 | 428 | 55.79 |
| Narayanan Shrikanth | 8 | 5558 | 439.23 |