![Google Showcases Latest Speech Technologies at INTERSPEECH 2023 in Dublin Google Showcases Latest Speech Technologies at INTERSPEECH 2023 in Dublin](https://aiheadliner.com/wp-content/uploads/https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhZ9tgKAAGviknbBlcGujLQ0tdvvu9tyvwCGble7iZ8jXSHMhYPEUI0rRiX0PwzFSK0Kx-vO6ByrqK20v_qhxE3xE6W0P4tGPQdFGx3OeZJVLOR-_Erh0-0qIE9YWLHuJiKjB5nXOpiPmTxg7Y4sT_m2WXn-uqPvZ7r9iySvCqfgo756D25jyw66KtFOEbi/w1200-h630-p-k-no-nu/Interspeech2023-Hero.jpg)
The 24th Annual Conference of the International Speech Communication Association (INTERSPEECH 2023) is currently taking place in Dublin, Ireland. This conference is known for being one of the largest gatherings of experts in the field of spoken language understanding and processing. Attendees have the opportunity to engage in oral presentations, poster sessions, and networking activities. Google is proud to be a Platinum Sponsor of INTERSPEECH 2023, where we are showcasing over 20 research publications and supporting various workshops and special sessions.
For those attending in-person, we invite you to visit the Google Research booth to meet our researchers, engage in Q&A sessions, and witness demonstrations of our latest speech technologies. These technologies aim to improve accessibility and enhance communication for billions of users around the world. If you are unable to attend in person, we encourage you to visit our virtual booth on Topia, where you can access up-to-date information on Google’s research and opportunities.
To stay updated on the activities happening at the Google booth, be sure to follow the @GoogleAI Twitter account. You can expect demos and Q&A sessions that will provide insights into the exciting work being presented at INTERSPEECH 2023.
Here are some of the notable papers and sessions that you can look forward to:
– Keynote talk – ISCA Medalist Survey Talk: Speech Compression in the AI Era by Jan Skoglund.
– Special session papers:
– Cascaded Encoders for Fine-Tuning ASR Models on Overlapped Speech by Richard Rose, Oscar Chang, Olivier Siohan.
– TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition by Hakan Erdogan, Scott Wisdom, Xuankai Chang*, Zalán Borsos, Marco Tagliasacchi, Neil Zeghidour, John R. Hershey.
These are just a few examples of the exciting research being presented at INTERSPEECH 2023. We are proud to contribute to this conference and to have the opportunity to collaborate with experts from around the world. If you are attending, we hope to see you there!
(Board and Organizing Committee list omitted)
(Papers list omitted)
*Work done while at Google.