Worldwide Convention on Acoustics, Speech and Sign Processing (ICASSP) 2023



Apple is sponsoring the Worldwide Convention on Acoustics, Speech and Sign Processing (ICASSP), which is able to happen in individual from June 4 – 10 in Rhodes Island, Greece. ICASSP is the IEEE Sign Processing Society’s flagship convention on sign processing and its functions. Beneath is the schedule of Apple sponsored workshops and occasions at ICASSP 2023.


Tuesday, June 6

Wednesday, June 7

Thursday, June 8

Friday, June 9

Accepted Papers

Audio-to-Intent Utilizing Acoustic-Textual Subword Representations from Finish-to-Finish ASR

Pranay Dighe, Prateeth Nayak, Oggi Rudovic, Erik Marchi, Xiaochuan Niu, Ahmed Tewfik

HEiMDaL: Extremely Environment friendly Methodology for Detection and Localization of wake-words

Arnav Kundu, Mohammad Samragh Razlighi, Minsik Cho, Priyanka Padmanabhan, Devang Naik

I See What You Hear: A Imaginative and prescient-inspired Methodology to Localize Phrases

Mohammad Samragh, Arnav Kundu, Ting-Yao Hu, Aman Chadha, Ashish Srivastava, Minsik Cho, Oncel Tuzel, Devang Naik

Enhancements to Embedding-Matching Acoustic-to-Phrase ASR Utilizing A number of-Speculation Pronunciation-Based mostly Embeddings

Hao Yen, Woojay Jeon

Studying to Detect Novel and Positive-Grained Acoustic Sequences Utilizing Pretrained Audio Representations

Vasudha Kowtha, Miquel Espi, Jonathan J Huang, Yichi Zhang, Carlos Avendano

Extra Talking or Extra Audio system?

Dan Berrebbi, Ronan Collobert, Navdeep Jaitly, Tatiana Likhomanenko

Naturalistic Head Movement Technology From Speech

Trisha Mittal, Zakaria Aldeneh, Masha Fedzechkina, Anurag Ranjan, Barry-John Theobald

Neural Transducer Coaching: Diminished Reminiscence Consumption with Pattern-wise Computation

Stefan Braun, Erik McDermott, Roger Hsiao

On the Function of Lip Articulation in Visible Speech Notion

Zakaria Aldeneh, Masha Fedzechkina, Skyler Seto, Katherine Metcalf, Miguel Sarabia, Nicholas Apostoloff, Barry-John Theobald

Much less Is Extra: A Unified Structure for Gadget-Directed Speech Detection with A number of Invocation Varieties

Oggi Rudovic, Wonil Chang, Vineet Garg, Pranay Dighe, Pramod Simha, Jack Berkowitz, Ahmed H. Abdelaziz, Sachin Kajarekar, Erik Marchi, Saurabh Adya

Pre-trained Mannequin Representations and their Robustness in opposition to Noise for Speech Emotion Evaluation

Vikramjit Mitra, Vasudha Kowtha, Hsiang-Yun Sherry Chien, Erdrin Azemi, Carlos Avendano

Textual content is All You Want: Personalizing ASR Fashions utilizing Controllable Speech Synthesis

Karren Yang, Ting-Yao Hu, Jen-Hao Rick Chang, Hema Swetha Koppula, Oncel Tuzel

Variable Consideration Masking for Configurable Transformer Transducer Speech Recognition

Pawel Swietojanski, Stefan Braun, Dogan Can, Thiago Fraga da Silva, Arnab Ghoshal, Takaaki Hori, Roger Hsiao, Henry Mason, Erik McDermott, Honza Silovsky, Ruchir Travadi, Xiaodan Zhuang


Please cease by the Apple sales space (quantity 16, situated subsequent to the Dome Bar primary entrance of the Rodos Palace Luxurious Conference Resort) anytime from Tuesday to Friday to work together with our demo.

Contextual Understanding in Siri

It is a demonstration of the context understanding know-how shipped in Siri. Customers can consult with an aforementioned entity utilizing anaphora or nominal ellipsis, consult with an entity on display, or right a earlier error by Siri or the consumer. Context understanding for Siri leverages a number of backend ML options similar to question rewriting and reference decision. This work is a step in direction of having extra pure conversations with Siri, and was shipped in iOS 16.

All ICASSP attendees are invited to cease by the Apple sales space (sales space quantity 16, situated subsequent to the Dome Bar primary entrance of the Rodos Palace Luxurious Conference Resort) to expertise this demo in individual.


Tatiana Likhomanenko, Arnav Kundu, Stefan Braun, Vikram Mitra, and Pawel Swietojanski are reviewers for ICASSP 2023.

Yannis Stylianou is a Seasonal College & Brief Course Chair for ICASSP 2023.

Ahmed Hussen Abdelaziz is the Meta Reviewer of SLT-L6: Language Modeling and Spoken Language Understanding for ICASSP 2023.

Let’s innovate collectively. Construct superb machine-learned experiences with Apple. Uncover alternatives for researchers, college students, and builders by visiting our Work with us web page.