Apple is sponsoring the 34th Interspeech conference, which will be held in Incheon, Republic of Korea from September 18 to 22. Interspeech is a global conference focused on cognitive intelligence for speech processing and application.

All Interspeech attendees are invited to stop by the Apple booth (booth number B5, located in the Grand Ballroom Lobby on the second floor of the Songdo ConvensiA) to check out our demo and chat with available recruiters and booth staff.

Schedule

Below is the schedule of Apple sponsored workshops and events. Visit the Interspeech 2022 website for the full conference schedule.

Saturday September 17

Monday September 19

Tuesday September 20

Wednesday September 21

Thursday September 22

Accepted Papers

Conference Accepted Papers

Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models

Vineet Garg, Ognjen (Oggi) Rudovic, Pranay Dighe, Ahmed H. Abdelaziz, Erik Marchi, Saurabh Adya, Chandra Dhir, Ahmed Tewfik

Emphasis Control for Parallel Neural TTS

Shreyas Seshadri, Tuomo Raitio, Dan Castellani, Jiangchuan Li

Improving Voice Trigger Detection with Metric Learning

Prateeth Nayak, Takuya Higuchi, Anmol Gupta, Shivesh Ranjan, Stephen Shum, Siddharth Sigtia, Erik Marchi, Varun Lakshminarasimhan, Minsik Cho, Saurabh Adya, Chandra Dhir, Ahmed Tewfik

Space-Efficient Representation of Entity-centric Query Language Models

Christophe Van Gysel, Mirko Hannemann, Ernest Pusateri, Youssef Oualil, Ilya Oparin

Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation

Vikramjit Mitra, Hsiang-Yun Sherry Chien, Vasudha Kowtha, Joseph Yitan Cheng, Erdrin Azemi

Vocal Effort Modeling in Neural TTS for Improving the Intelligibility of Synthetic Speech in Noise

Tuomo Raitio, Petko Petkov, Jiangchuan Li, Muhammed Shifas, Andrea Davis, Yannis Stylianou

Acknowledgements

Rin Metcalf Susa is a member of the Speaking Styles and Interaction Styles Special Session Scientific Committee at Interspeech 2022.

Lyan Verwimp, Mirko Hannemann, Shreyas Seshadri, Tuomo Raitio, Barry Theobald, Zak Aldeneh, and Vikram Mitra are reviewers for Interspeech 2022.

Let's innovate together. Build amazing machine-learned experiences with Apple. Discover opportunities for researchers, students, and developers by visiting our Work with us page.

Related readings and updates.

ECCV 2022

Apple is sponsoring the European Conference on Computer Vision (ECCV), which will be held in Tel Aviv, Israel from October 23 to 27. ECCV is the top European conference in the image analysis area.

See event details

Vocal Effort Modeling in Neural TTS for Improving the Intelligibility of Synthetic Speech in Noise

We present a neural text-to-speech (TTS) method that models natural vocal effort variation to improve the intelligibility of synthetic speech in the presence of noise. The method consists of first measuring the spectral tilt of unlabeled conventional speech data, and then conditioning a neural TTS model with normalized spectral tilt among other prosodic factors. Changing the spectral tilt parameter and keeping other prosodic factors unchanged…
See paper details