• Publications
  • Influence
Machine learning and natural language processing in psychotherapy research: Alliance as example use case.
TLDR
Machine learning and natural language processing are introduced as related methodologies that may prove valuable for automating the assessment of meaningful aspects of treatment in mental health care and psychotherapy.
Language Features for Automated Evaluation of Cognitive Behavior Psychotherapy Sessions
TLDR
This work examines how linguistic features can be effectively used to develop an automatic competency rating tool for CBT, and suggests that a real-world system could be developed to automatically evaluate CBT sessions to assist training, supervision, or quality assurance of services.
Using Prosodic and Lexical Information for Learning Utterance-level Behaviors in Psychotherapy
TLDR
It is demonstrated that prosodic features provide discriminative information relevant to the behavior task and show that they improve prediction when fused with automatically derived lexical features.
Linguistically Aided Speaker Diarization Using Speaker Role Information
TLDR
This work aims to utilize linguistic information as a supplemental modality to identify the various speakers in a more robust way on conversational scenarios where the speakers assume distinct roles and are expected to follow different linguistic patterns.
Combined Speaker Clustering and Role Recognition in Conversational Speech
TLDR
This work proposes the integration of an audio-based speaker clustering algorithm with a language-aided role recognizer into a meta-classifier which takes both modalities into account and shows that it yields superior results for the SRR task.
Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions
TLDR
An end-to-end pipeline that converts speech audio to diarized and transcribed text and extracts linguistic features to code the CBT sessions automatically and a novel method to augment the word-based features with the utterance level tags for subsequent CBT code estimation is proposed.
Automated quality assessment of cognitive behavioral therapy sessions through highly contextualized language representations
TLDR
A BERT-based model is proposed for automatic behavioral scoring of a specific type of psychotherapy, called Cognitive Behavioral Therapy (CBT), where prior work is limited to frequency-based language features and/or short text excerpts which do not capture the unique elements involved in a spontaneous long conversational interaction.
The Second DIHARD Challenge: System Description for USC-SAIL Team
TLDR
This paper describes components that form a part of USCSAIL team’s submissions to Track 1 and Track 2 of the second DIHARD speaker diarization challenge, and proposes a clustering scheme based on spectral clustering that yields competitive performance.
"Am I A Good Therapist?" Automated Evaluation Of Psychotherapy Skills Using Speech And Language Technologies
TLDR
An automated competency rating tool able to process the raw recorded audio of a session, analyzing who spoke when, what they said, and how the health professional used language to provide therapy is developed.
Identifying Therapist and Client Personae for Therapeutic Alliance Estimation
TLDR
The results show that alliance can be explained by the interactions between the discovered character types, and models trained on therapist and client personae achieve significant performance gains compared to competitive supervised baselines.
...
1
2
...