ASSTA within Interspeech 2026

Monday 28 September 2026

Date & time	Session ID / track	Presentation title	Full author list, showing ASSTA members
11:00–13:00	Poster 2585 — Area 2 — Poster 1: Tools and Techniques for Phonetic Analysis	Reconciling Dynamic Data Analysis with Linguistic Reality: Comparing Legendre Polynomial Modelling and GAMM Applied to Prosodic Contact Paper ID 2585 (poster)	Angelo Dian (University of Oxford, ASSTA member); Mary Baltazani (University of Oxford); Spyros Armostis (University of Cyprus); Elinor Payne (University of Oxford)
11:00–13:00	Poster 2610 — Area 2 — Poster 1: Tools and Techniques for Phonetic Analysis	Achieving voicelessness in coda stop contexts: Insights from combined electroglottography and laryngoscopy Paper ID 2610 (poster)	Joshua Penney (Macquarie University, ASSTA member); Jae Hyun Kim (Macquarie University); Dijana Dragicevich (Macquarie University); Prue Gourley (Macquarie University)
12:20–12:40	Area 5 — Oral 1 (Spatial Audio 1) — Paper ID 1618	BiEAR: A Human Auditory‑Inspired Adaptive Binaural Front-end for Multi‑Speaker Localisation and Distance Estimation Paper ID 1618 (oral)	Hanyu Meng (UNSW Sydney, ASSTA member); Eliathamby Ambikairajah (UNSW Sydney); Vidhyasaharan Sethu (UNSW Sydney, ASSTA member); Qiquan Zhang (Alibaba Group); Haizhou Li (CUHK‑Shenzhen)
14:30–16:30	Special Session 1495 — Methods and data for vocal tract and articulation analysis	Tongue-Shape Strategies for Standard Mandarin Retroflex Sibilants: A Preliminary Ultrasound and Unsupervised Clustering Study Paper ID 1495 (poster)	Zixi Jing (University of Auckland, ASSTA member); C. T. Justine Hui (University of Auckland); Karen Huang (University of Auckland); Catherine I. Watson (University of Auckland, ASSTA member)
14:30–16:30	Special Session 1890 — Morphoacoustic / 3D vocal tract modelling	Morphoacoustic Modeling of a Dynamic 3D Vocal Tract Using MRI‑Constrained Deformations and FEM Acoustics Paper ID 1890 (poster)	Tharinda Piyadasa (University of Sydney); Michael Proctor (Macquarie University, ASSTA member); Tünde Szalay (University of Sydney, ASSTA member); Joan Glaunès (Université Paris Cité); Amelia Gully (University of York); Kirrie Ballard (University of Sydney); Emily Kiff (University of York); Naeim Sanaei (Westmead Hospital); Sheryl Foster (University of Sydney); David Waddington (University of Sydney); Craig Jin (University of Sydney, ASSTA member)
14:50–15:10	Area 13 — Oral 1 (Assistive Technologies 1)	Adaptation to Room Acoustics in Understanding Vocoded Speech: A Comparison Between Listeners With Varying Immersion Age Paper ID 113 (oral)	Epri Pratiwi (University of Auckland, ASSTA member); C. T. Justine Hui (University of Auckland); Yusuke Hioka (University of Auckland)

Tuesday 29 September 2026

Date & time	Session ID / track	Presentation title	Full author list, showing ASSTA members
9.40–10.00am	Area 2 — Voice Quality Aspects of Speech	An investigation of post‑stop breathiness in Australian English Paper ID 1555 (oral)	Thomas Powell‑Davies (Australian National University, ASSTA member); Rosey Billington (Australian National University, ASSTA member)
10.00–10.20am	Area 2 — Voice Quality Aspects of Speech	Acoustic correlates of voice quality settings: variation within and between individual speakers Paper ID 2053 (oral)	Alice Paver (University of Cambridge); Kirsty McDougall (University of Cambridge, ASSTA member)
09:00–11:00	Area 3 — Poster 3 — Speech Emotion Recognition and Representation 2	Revisiting Delay Compensation via Feature‑Level Temporal Accumulation in Continuous Emotion Recognition Paper ID 3030 (poster)	Jian Xiang (The University of New South Wales); Jingyao Wu (Massachusetts Institute of Technology); Ting Dang (University of Melbourne); Vidhyasaharan Sethu (The University of New South Wales, ASSTA member); Eliathamby Ambikairajah (The University of New South Wales)
09:00–11:00	Area 5 — Poster 5 — Audio signal analysis	Automatic identification of the onset of creaky voice according to F0 instability Paper ID 1430 (poster)	Rasmus Puggaard‑Rode (University of Oxford); Joshua Penney (Macquarie University, ASSTA member)
09:00–11:00	Area 14 — Special Session — Pacific Voices: Speech Science and Technology for the Languages of the Pacific Ocean	A preliminary exploration of stop-vowel coarticulation in Māori Paper ID 1456 (oral, within special session)	Isabella Shields (University of Auckland); Hiraia Haami-Wells (University of Auckland); C. T. Justine Hui (University of Auckland); Peter J. Keegan (University of Auckland); Catherine I. Watson (ASSTA member, University of Auckland)
09:00–11:00	Area 14 — Special Session — Pacific Voices: Speech Science and Technology for the Languages of the Pacific Ocean	Continual Adaptation for Pacific Indigenous Speech Recognition Paper ID 2215 (oral, within special session)	Yang Xiao (ASSTA member, The University of Melbourne), Aso Mahmudi (The University of Melbourne), Nick Thieberger (The University of Melbourne), Eliathamby Ambikairajah (UNSW Sydney), Eun-Jong Holden (The University of Melbourne), Ting Dang (The University of Melbourne)
09:00–11:00	Area 14 — Special Session — Pacific Voices: Speech Science and Technology for the Languages of the Pacific Ocean	Mapping Acceptable Pronunciation Range for Te Reo Māori through Perceptual, Acoustic, and Marker Evaluative Data Paper ID 1561 (oral, within special session)	Zoe E. Evans (University of Auckland); Catherine I. Watson (ASSTA member, University of Auckland); Peter J. Keegan (University of Auckland); Jesin James (University of Auckland, ASSTA member); Piata Allen (University of Auckland)
09:00–11:00	Area 14 — Special Session — Pacific Voices: Speech Science and Technology for the Languages of the Pacific Ocean	Oral stop realisation in three French Polynesian languages Paper ID 899 (oral, within special session)	Janet Fletcher (University of Melbourne, ASSTA member); Adele Gregory (University of Melbourne, ASSTA member)
09:00–11:00	Area 14 — Special Session — Pacific Voices: Speech Science and Technology for the Languages of the Pacific Ocean	Pā-Kakare: The First Emotional Speech Database for Te Reo Māori Paper ID 1543 (oral, within special session)	Himashi Rathnayake (ASSTA member, University of Auckland); Jesin James (ASSTA Member, University of Auckland); Ake Nicholas (University of Auckland); Gianna Leoni (Te Hiku Media); Catherine I. Watson (ASSTA member, University of Auckland); Peter J. Keegan (University of Auckland)
10:20–10:40	Area 2 — Voice Quality Aspects of Speech	Phonetic evidence for contrastive voicing in Nakanamanga coronal plosives Paper ID 2832 (oral)	Shubo Li (Australian National University, ASSTA member)
14:00–16:00	Area 7 — Oral 5 — Speech Synthesis Evaluation 1	Phonetically Grounded Vowel Space Metrics for Evaluating Synthetic Speech During TTS Model Training Paper ID 1579 (oral)	Pasindu Udawatta (ASSTA member, University of Auckland); Jesin James (ASSTA, University of Auckland); Ake Nicholas (University of Auckland); B. T. Balamurali (Independent Researcher); C. I. Watson (University of Auckland)
16:30–18:30	Area 14 — 9 — Special Session — Queer and Trans Speech Science and Technology	Masculinity and Sexual Orientation as Predictors of f0 Variation in the Speech of Australian English Speaking Men Paper ID 1906 (poster)	Timothy Shea (ASSTA member, Macquarie University); Hannah White (LMU Munich); Joshua Penney (Macquarie University, ASSTA member); Anita Szakay (Macquarie University); Felicity Cox (Macquarie University, ASSTA member)
16:30–18:30	Area 14 — 9 — Special Session — Queer and Trans Speech Science and Technology	The First Dravidian Speech Datasets for Transphobic and Homophobic Hate Speech: Multimodal Benchmarking Paper ID 2368	K N Laksmi (Amrita Vishwa Vidyapeetham), K Hemavardhan Reddy (Amrita Vishwa Vidyapeetham), A Venkata Satya (Amrita Vishwa Vidyapeetham), Kota Venkata Vamshidhar Reddy (Amrita Vishwa Vidyapeetham), Jyothish Lal G (Amrita Vishwa Vidyapeetham), Premjith B (Amrita Vishwa Vidyapeetham), Jesin James (University of Auckland, ASSTA member),
17:50–18:10	Area 2 — Oral 2 — Prominence, Stress and Focus	Broad Focus Rise(-fall) Declaratives in Venetan: Investigating Typological Outliers in Italo-Romance Intonation Paper ID 2691 (oral)	Elinor Payne (University of Oxford); Angelo Dian (ASSTA member, University of Oxford)

Wednesday 30 September 2026

Date & time	Session ID / track	Presentation title	Full author list, showing ASSTA members
09:20–09:40	Area 5 — Oral 4 — Evaluation, Benchmarking, and Reliability of Audio Systems	The First Environmental Sound Deepfake Detection Challenge: Benchmarking Robustness, Evaluation, and Insights Paper ID 1599 (oral)	Han Yin (KAIST); Yang Xiao (University of Melbourne, ASSTA member); Rohan Kumar Das (Fortemedia); Jisheng Bai (Xi'an University of Posts & Telecommunications; Xi'an Lianfeng Acoustic Technologies Co., Ltd.); Ting Dang, (University of Melbourne)
09:00–11:00	Area 2 — Poster 3 — Phonetic Aspects of TTS and ASR Systems	Assessing the effect of volitional and synthetic pitch raising in female speakers on automatic speaker recognition Paper ID 444 (poster)	Chloe Patman (University of Cambridge); Linda Gerlach (Oxford Wave Research); Anil Alexander (Oxford Wave Research); Finnian Kelly (Oxford Wave Research); Kirsty McDougall (University of Cambridge, ASSTA member)
09:00–11:00	Area 14 — 5 — Special Session — Challenges in Speech Data Collection, Curation, and Annotation	Pronunciation and Intonation Structured Markup (PRISM): A Dataset for Australian English Pronunciation Feedback Paper ID 2830 (poster)	Olga Maxwell (University of Melbourne, ASSTA member); Uy Thinh Quang (University of Melbourne); Debbie Loakes (University of Melbourne, ASSTA member); Adele Gregory (University of Melbourne, ASSTA member); Robert Turnbull (University of Melbourne)
15:20–15:40	Area 1 — Oral 2 — Neurophysiology of Speech	Bayesian Generalized Additive Multilevel Models for Accurate ERP Latency Estimation under Moderate Downsampling Paper ID 2750 (oral)	Zixia Fan (Macquarie University, ASSTA member); Ronny Kurniawan Ibrahim (Macquarie University); Joshua Penney (Macquarie University, ASSTA member); Felicity Cox (Macquarie University, ASSTA member)
15:20–15:40	Area 8 — Oral 3 — Domain Adaptation & Accented ASR	Activation Steering for Accent Adaptation in Large Audio Language Models Paper ID 2166 (oral)	Jinuo Sun (The University of Melbourne); Yang Xiao (The University of Melbourne, ASSTA member); Sung Kyun Chung (The University of Melbourne); Qiuchi Hu (The University of Melbourne); Gongping Huang (Wuhan University); Eun-Jung Holden (The University of Melbourne); Ting Dang (The University of Melbourne)
14:00–16:00	Area 2 — Poster 5 — Speaker-Specific, Forensic and Segmental Characteristics of Typical and Atypical Speech	Effects of body position on vowel formants in New Zealand English Paper ID 1545 (oral)	Qing Guan (The University of Auckland, ASSTA member); Catherine I. Watson (The University of Auckland); C. T. Justine Hui (The University of Auckland)
14:00–16:00	Area 2 — Poster 5 — Speaker-Specific, Forensic and Segmental Characteristics of Typical and Atypical Speech	An Acoustic Investigation of Mid Front Vowel Harmony in Assamese Paper ID 3034 (poster)	Saurabh Nath (The Australian National University); Rosey Billington (The Australian National University, ASSTA member); Danielle Barth (The Australian National University)
16:00–16:30	Regular afternoon tea session — The Gallery, Level 2 MEET ON THE RIGHT OF THE REGISTRATION DESK	ASSTA get together – Celebrating 40 years of ASSTA.	All ASSTA members welcome!
17:10–17:30	Area 2 — Oral 3 — Diphthongs and Monophthongs	Phonetic evidence for contrastive length in Nakanamanga monophthongs Paper ID 1597 (oral)	Shubo Li (Australian National University, ASSTA member)
17:50–18:10	Area 2 — Oral 3 — Diphthongs and Monophthongs	Modelling diphthong dynamics: A GAMM-based analysis of Australian English diphthongs Paper ID 2861 (oral)	Ksenia Gnevsheva (Australian National University); Canaan Lan (University of Melbourne, ASSTA member); Gerard Docherty (Griffith University, ASSTA member); Catherine Travis (Australian National University)
16:30–18:30	Area 4 — Poster 3 — Speech and Language Representation	Quantifying Dimensional Independence in Speech: An Information-Theoretic Framework for Disentangled Representation Learning Paper ID 1654 (poster)	Bipasha Kashyap (Deakin University, ASSTA member); Björn W. Schuller (TUM University Hospital; Imperial College London); Pubudu N. Pathirana (Deakin University)
16:30–18:30	Area 4 — Poster 3 — Speech and Language Representation	Hybrid Continual Learning for Low-Resource Australian Aboriginal Language Identification Paper ID 1789 (poster)	Pravina Mylvaganam (University of New South Wales); Ting Dang (University of Melbourne); Eliathamby Ambikairajah (University of New South Wales); Vidhyasaharan Sethu (University of New South Wales, ASSTA member); Jingyao Wu (Massachusetts Institute of Technology)
16:30–18:30	Show And Tell 5 — Speech Analysis, Data Resources and Research Tools	SpeechBench: A Unified Speech Annotation and Analysis Tool Paper ID 3600 (show and tell)	Zheng Nan (University of New South Wales); Tharmakulasingam Sirojan (University of New South Wales); Mostafa Shahin (University of New South Wales); Tünde Szalay (University of Sydney, ASSTA member); Vidhyasaharan Sethu (University of New South Wales, ASSTA member); Beena Ahmed (University of New South Wales)

Thursday 1 October 2026

Date & time	Session ID / track	Presentation title	Full author list, showing ASSTA members
09:00–11:00	Poster 1563 — Area 10 — Poster 1: Multimodal Speech Processing and Speech LLM Systems	MultiEmoVec: Learning Generalised Multimodal Emotion Representation by Momentum Contrast and Multi-task Reconstruction Paper ID 1563 (poster)	Junchen Liu (University of Auckland, ASSTA member); Jesin James (Electrical, Computer and Software Engineering, University of Auckland, New Zealand, ASSTA member); Karan Nathwani (India Institute of Technology); Michael Witbrock (Computer Science, University of Auckland, New Zealand)
09:00–11:00	Special Session 2466 — Area 14 — Special Session: Post-Training of Speech Foundation Models	PolyBench: A Benchmark for Compositional Reasoning in Polyphonic Audio Paper ID 2466 (poster)	Yuanjian Chen (Harbin University of Science and Technology); Yang Xiao (The University of Melbourne, ASSTA member); Han Yin (KAIST); Xubo Liu (University of Surrey); Jinjie Huang (Harbin University of Science and Technology); Ting Dang (The University of Melbourne)
09:00–11:00	Special Session 2066 — Area 14 — Special Session: Post-Training of Speech Foundation Models	Localizing and Editing Knowledge in Large Audio-Language Models Paper ID 2066 (poster)	Sung Kyun Chung (The University of Melbourne); Jiaheng Dong (The University of Melbourne, ASSTA member); Qiuchi Hu (The University of Melbourne); Jinuo Sun (The University of Melbourne); Gongping Huang (Wuhan University); Hong Jia (University of Auckland); Ting Dang (The University of Melbourne)
12.45–14:00	Level 2, meeting room C2.1	ASSTA AGM	ALL ASSTA MEMBERS WELCOME (hybrid also enabled for non-Interspeech attendees)
15:20–15:40	Area 2 — Oral 4 — Gender- and Age-Related Speech Characteristics	Listeners' gendered experiences and beliefs affect iconic pitch associations Paper ID 1642 (oral)	Sasha Calhoun (Victoria University of Wellington, ASSTA member); Paul Warren (Victoria University of Wellington); Sara Gilbert (Victoria University of Wellington) presented by ASSTA member Chloé Diskin-Holdaway (The University of Melbourne)
14:00–16:00	Poster 3116 — Area 1 — Poster 3: Speech Production and Perception 2	Lexical stress-conditioned spatiotemporal gestural coordination in L2 English Paper ID 3116 (poster)	Paul McGuire (Macquarie University; National Tsing Hua University, ASSTA member); Michael Proctor (Macquarie University, ASSTA member); Feng-fan Hsieh (National Tsing Hua University); Yueh-chin Chang (National Tsing Hua University)
14:00–16:00	Poster 2031 — Area 3 — Poster 4: Speech Emotion Recognition and Representation 3	Disentangling Reasoning in Large Audio-Language Models for Ambiguous Emotion Prediction Paper ID 2031 (poster)	Xiaofeng Yu (University of Auckland); Jiaheng Dong (The University of Melbourne, ASSTA member); Jean Honorio (The University of Melbourne; ARC OPTIMA); Abhirup Ghosh (University of Birmingham); Hong Jia (University of Auckland); Ting Dang (The University of Melbourne)

Keep up to date.

with news about upcoming events, job announcements, or news about the Association through our ASSTA Newsletter.

Create a free account

Pointer up

Decoration