International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025

Schedule

Stop by the Apple booth from April 6 to 11 from 09:00 to 17:00 at Booth C3 in the Hyderabad International Convention Center. All times listed are in GMT +5:30.

Monday, April 7

• WORKSHOP KEYNOTE TALK
• FLute: Federated Learning for Audio Understanding
• 09:00 - 10:00
• Location: Hall 4
• Private Federated Learning for Speech Recognition
• Tatiana Likhomanenko

Wednesday, April 9

• ORAL PRESENTATION
• Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition
• 09:00 - 09:10, Enhancing ASR with Large Language Models, Room MRG.04
• Takaaki Hori, Martin Kocour (Brno University of Technology), Adnan Haider, Erik McDermott, Xiaodan Zhuang

• ORAL PRESENTATION
• Contextualization of ASR with LLM Using Phonetic Retrieval-Based Augmentation
• 09:30 - 09:40, Enhancing ASR with Large Language Models, Room MRG.04
• Zhihong Lei, Xingyu Na, Mingbin Xu, Ernest Pusateri, Christophe Van Gysel, Yuanyuan Zhang, Shiyi Han (Character AI), Zhen Huang

• POSTER
• Retrieval-Augmented Correction of Named Entity Speech Recognition Errors
• 11:30 - 13:00, Advances in LLMs and E2E Architectures for ASR, Room Poster 2F
• Ernest Pusateri, Anmol Walia, Anirudh Kashi, Bortik Bandyopadhyay, Nadia Hyder, Sayantan Mahinder, Raviteja Anantha, Daben Liu (Capital One), Sashank Gondala (Further AI)

• ORAL PRESENTATION
• An Efficient and Streaming Audio Visual Active Speaker Detection System
• 11:45 - 11:55, Image and Video Content Analysis I, Room MR1.04
• Arnav Kundu, Yanzi Jin, Max Horton, Mohammad Sekhavat, Danny Tormoen, Devang Naik

• ORAL PRESENTATION
• ImmerseDiffusion: Generative Spatial Audio Latent Diffusion Model
• 11:45 - 11:55, Sound Generation and Synthesis II, Room MR1.02
• Moji Heydari (University of Rochester), Mehrez Souden, Josh Atkins, Bruno Conejo

• NETWORKING LUNCHEON
• Women in Signal Processing (WiSP)
• 13:00 - 15:00
• Location: HICC Architecture Room
• Ahmed Tewfik and colleagues will be representing Apple at the Women in Signal Processing Luncheon.

• INDUSTRY FORUM TALK
• ICASSP 2025 Industry Forum
• 14:00 - 14:30
• Location: Industry Forum Hall
• Integrating Large Language Models with Distributed Systems: Architecture Patterns, Challenges and Innovations
• Venkataramanan Subramanian

• PLENARY TALK
• IEEE Norbert Weiner Plenary Talk
• 15:45 - 16:45
• Location: Room Hall 4
• Bridging Generative AI and Statistical Signal Processing
• Ahmed Tewfik

• POSTER
• Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector Based Pseudo-Labels
• 17:00 - 18:30, Speaker Recognition II, Room Poster 2D
• Shinji Watanabe (Carnegie Mellon University), Jeeweon Jung (Carnegie Mellon University), Ahmed Hussen Abdelaziz, Takuya Higuchi, Zak Aldeneh, Li-Wei Chen (Carnegie Mellon University), Stephen Shum, Tatiana Likhomanenko, Barry-John Theobald

Thursday, April 10

• POSTER
• SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions
• 08:30 - 10:00, Novel Audio, Speech and Language Modeling Techniques, Room Poster 2D
• Dominik Wagner (Friedrich-Alexander-Universitaet Erlangen-Nuernberg), Alex Churchill, Siddharth Sigtia, Erik Marchi

• POSTER
• SLiCK: Exploiting Subsequences for Length-Constrained Keyword Spotting
• 08:30 - 10:00, Audio-Visual and Robust Speech Synthesis, Room Poster 2C
• Kumari Nishu, Minsik Cho, Devang Naik

• POSTER
• Towards Automatic Assessment of Self-Supervised Speech Models using Rank
• 08:30 - 10:00, Speech Datasets and Model Assessment, Room Poster 2F
• Zak Aldeneh, Vimal Thilak, Takuya Higuchi, Tatiana Likhomanenko, Barry Theobald

• ORAL PRESENTATION
• Compact Neural TTS Voices for Accessibility
• 09:15 - 09:25, TTS Architecture, Room MRG.04
• Kunal Jain, Eoin Murphy, Deepanshu Gupta, Jonathan Dyke, Saumya Hiren Shah, Vasileios Tsiaras, Petko Petkov, Alistair Conkie

• ORAL PRESENTATION
• Exploring Prediction Targets in Masked Pre-training for Speech Foundation Models
• 15:00 - 15:10, Multilingual Speech Processing and Identification, Room MRG.04
• Li-Wei Chen (Carnegie Mellon University), Zak Aldeneh, Takuya Higuchi, Tatiana Likhomanenko, Richard Bai, Ahmed Hussen Abdelaziz, Barry Theobald