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
-
Industry liaison co-chair
-
Andreas StolckeIndustry session co-chair
-
Speech recognition area chair
Accepted publications
Tutorials
Interspeech 2022 Tutorial on Self-supervised Representation Learning for Speech Processing Hybrid
September 18
This tutorial session will present self-supervised speech representation learning approaches and their connection to related research areas. Since many current methods focus solely on automatic speech recognition as a downstream task, we will review recent efforts on benchmarking learned representations to extend the application of such representations beyond speech recognition. A hands-on component of this tutorial will provide practical guidance on building and evaluating speech representation models.
Amazon speakers: Katrin Kirchhoff
Website: https://interspeech2022.org/program/tutorials.php
Amazon speakers: Katrin Kirchhoff
Website: https://interspeech2022.org/program/tutorials.php
Interspeech 2022 Tutorial on Personalized Speech Enhancement: Data and Resource-Efficient Machine Learning
September 18
In this tutorial, we will explore various definitions of personalized speech enhancement in the literature and relevant machine learning concepts, such as zero- or few-shot learning approaches, data augmentation and purification, self-supervised learning, knowledge distillation, and domain adaptation. We will also see how these methods can improve data and resource efficiency in machine learning while achieving desired speech enhancement performance.
Amazon speaker: Minje Kim
Website: https://interspeech2022.org/program/tutorials.php
Amazon speaker: Minje Kim
Website: https://interspeech2022.org/program/tutorials.php
-
August 23, 2023Senior principal scientist Jasha Droppo on the shared architectures of large language models and spectrum quantization text-to-speech models — and other convergences between the two fields.
-
August 16, 2023Learning to represent truncated sentences with semantic graphs improves models’ ability to infer missing content.
-
December 20, 2022Ariadna Sanchez, a scientist who works in polyglot text to speech, draws on her musical background to help find novel solutions.
-
November 17, 2022In 2022, the Alexa Trustworthy AI team helped organize a workshop at NAACL and a special session at Interspeech.