Overview
Interspeech is a technical conference focused on speech processing and application, emphasizing interdisciplinary approaches addressing all aspects of speech science and technology, ranging from basic theories to advanced applications.
Amazon organizing committee members
-
Julia Hirschberg (Amazon Scholar)Organizing committee member, diversity and inclusion
-
Area chair, speech recognition — signal processing, acoustic modeling robustness, and adaptation
-
Area chair, spoken dialog systems and conversational analysis
-
SSW 11 Session chair, synthesis and context
Accepted publications
Workshops, satellites, and special sessions
Interspeech 2021 Workshop on Speech Synthesis (SSW11)
August 26 - August 28
Amazon presenters: Thomas Drugman, Pilar Oplustil-Gallegos, Goeric Huybrechts, Bartek Perz, Jaime Lorenzo-Trueba, Abdelhamid Ezzerg, Adam Gabrys, Bartosz Putrycz, Daniel Korzekwa, Daniel Saez-Trigueros, David McHardy, Kamil Pokora, Viacheslav Klimkov, Raahil Shah, Kamil Pokora, Viacheslav Klimkov, Thomas Merritt, Alejandro Mottini, Sri Karlapati, Ammar Abbas, Bajibabu Bollepalli, Alexis Moinet, Arnaud Joly, Penny Karanasou, Peter Makarov, Simon Slangens
Website: https://ssw11.hte.hu/en/
Website: https://ssw11.hte.hu/en/
Interspeech 2021 Workshop on Speech, Music and Mind (SMM21)
August 27
Interspeech 2021 Special Session on Privacy-preserving Machine Learning for Audio, Speech, and Language Processing
August 30
Interspeech 2021 Special Session on Non-Autoregressive Sequential Modeling for Speech Processing
September 2
Interspeech 2021 Workshop on Machine Learning in Speech and Language Processing
September 6
Interspeech 2021 Workshop on Satellite: Text, Speech, and Dialogue (TSD 2021)
September 6 - September 9
Interspeech 2021 Workshop on Machine Learning Challenges for Hearing Aids
September 16 - September 17
-
February 02, 2022Sessions on multidevice scenarios, inclusive and fair speech technologies, trustworthy speech processing, and speech intelligibility prediction seek paper submissions.
-
September 23, 2021Droppo discusses his work in the field of speech recognition and signal processing.
-
September 10, 2021Data augmentation makes examples more realistic, while continual-learning techniques prevent “catastrophic forgetting”.
-
September 09, 2021Model using ASR hypotheses as extra inputs reduces word error rate of human transcriptions by almost 11%.