Program Schedule

[22&23-08-2025]: Workshop on Child Computer Interaction

Schedule

22-08-2025 (Friday)

• - 12:00- 13:00: Lunch

• - 13:00-14:20 Welcome and Oral Session I: Models

13:00- 13:05: Welcome ceremony

13:10-13:30: G-IFT: A Gated Linear Unit adapter with Iterative Fine-Tuning for Low-Resource Children's Speaker Verification. Vishwas Shetty (UCLA)*; Jiusi Zheng (UCLA); Abeer Alwan (UCLA) [paper]

13:35-13:55: Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet. Anyu Ying (Carnegie Mellon University)*; Natarajan Balaji Shankar (University of California Los Angeles); Chyi-Jiunn Lin (Carnegie Mellon University); Mohan Shi (University of California Los Angeles); Pu Wang (KU Leuven); Hye-jin Shim (Carnegie Mellon University); Siddhant Arora (Carnegie Mellon University); Hugo Van hamme (KU Leuven); Abeer Alwan (University of California Los Angeles); Shinji Watanabe (Carnegie Mellon University). [paper]

14:00-14:20: Speech transformer models for extracting information from baby cries. Guillem Bonafos (Université Jean Monnet )*; Jérémy Rouch (Université Jean Monnet); Lény Lego (Université Jean Monnet); David Reby (Université Jean Monnet); Hugues Patural (Université Jean Monnet); Nicolas Mathevon (Université Jean Monnet); Rémi Emonet (Université Jean Monnet) [paper]

• - 14:20-14:30 Coffee Break

• - 14:30-16:00 Poster Session I: Application (joint with SLaTE)

Enhancing Child-Adult Directed Speech: ASR for Progress Monitoring in Preschool Settings. Rasa Lileikyte (University of Texas at Dallas)*; Dwight Irvin (University of Florida); John H. L. Hansen (University of Texas at Dallas) [paper]

Little Voices, Big Discoveries – Using Speaker Diarization to Assess Parent-Child Engagement within a Science Museum Scenario. Satwik Dutta (The University of Texas at Dallas)*; Abhejay Murali (The University of Texas at Austin); Jay Buzhardt (The University of Kansas); Dwight Irvin (The University of Florida); John Hansen (The University of Texas at Dallas) [paper]

Assessing Finnish L2 Speech in School Children via Retrieval-Augmented In-Context Learning on Unseen Tasks. Ekaterina Voskoboinik (Aalto University)*, Mikko Kurimo (Aalto University) [paper]

Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions.Aditya Asvin (University of Southern California ); Rimita Lahiri (University of Southern California ); Aditya Kommineni (University of Southern California ); Somer Bishop (University of California San Francisco); Catherine Lord (University of California Los Angeles); Sudarsana Kadiri (University of Southern California)*; Shrikanth Narayanan (University of Southern California ) [paper]

• - 16:00-16:15 Coffee Break

• - 16:15-17:10 Keynote: Dr. Titia Benders (joint with SLaTE) - "Understanding Child Speech – What speech sounds in context reveal about developing Encoding and Articulation"

• - 18:30 Dinner (joint with SLaTE)

23-08-2025 (Saturday)

• - 08:30-10:00 Oral Session II: Robust Speech

08:30- 08:50: Adapting Whisper for Lightweight and Efficient Automatic Speech Recognition of Children for On-device Edge Applications. Satwik Dutta (The University of Texas at Dallas)*; Shruthigna Chandupatla (The University of Texas at Dallas, USA); John Hansen (The University of Texas at Dallas, USA) [paper]

08:55-9:15: An Age-Agnostic System for Robust Speaker Verification. Jiusi Zheng (UCLA)*; Vishwas Shetty (UCLA); Natarajan Balaji Shankar (UCLA); Abeer Alwan (UCLA). [paper]

09:15-35: Personalised Children's Automatic Speech Recognition using Text-To-Speech.Thomas Rolland (University Superior Tecnico Lisboa & INESC-ID)*; Alberto Abad (University Superior Tecnico Lisboa & INESC-ID) [paper]

09:40- 10:00: Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children’s Speech. ABHIJIT SINHA (NATIONAL INSTITUTE OF TECHNOLOGY SIKKIM)*; Harishankar Kumar (NATIONAL INSTITUTE OF TECHNOLOGY SIKKIM); Mohit Joshi (NATIONAL INSTITUTE OF TECHNOLOGY SIKKIM); Hemant Kumar Kathania (NATIONAL INSTITUTE OF TECHNOLOGY SIKKIM); Shrikanth Narayanan (University of Southern California ); Sudarsana Reddy Kadiri (University of Southern California) [paper]

• - 10:00-10:30 Coffee Break

• - 10:30-11:30 Hot seat Discussion + Closing Marks

Topics: Ethical Consideration of AI in Education, Future of WOCCI

• - 12:00: Lunch

Accepted Papers

[Congratulations!]

Kindly follow Interspeech poster presentation guidelines [Link].

Robust Speech

Adapting Whisper for Lightweight and Efficient Automatic Speech Recognition of Children for On-device Edge Applications (Satwik Dutta)
An Age-Agnostic System for Robust Speaker Verification (Jiusi Zheng)
Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children’s Speech (ABHIJIT SINHA)
Personalised Children's Automatic Speech Recognition using Text-To-Speech (Thomas Rolland)

Applications

Enhancing Child-Adult Directed Speech: ASR for Progress Monitoring in Preschool Settings (Rasa Lileikyte)
Little Voices, Big Discoveries – Using Speaker Diarization to Assess Parent-Child Engagement within a Science Museum Scenario (Satwik Dutta)
Assessing Finnish L2 Speech in School Children via Retrieval-Augmented In-Context Learning on Unseen Tasks (Ekaterina Voskoboinik)
Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions (Sudarsana Kadiri)

Models

G-IFT: A Gated Linear Unit adapter with Iterative Fine-Tuning for Low-Resource Children's Speaker Verification (Vishwas Shetty)
Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet (Anyu Ying)
Speech transformer models for extracting information from baby cries (Guillem Bonafos)