Open AccessThe Zero Resource Speech Challenge 2020: Discovering Discrete Subword and Word Units
Author(s) -
Ewan Dunbar,
Julien Karadayi,
Mathieu Bernard,
Xuan-Nga Cao,
Robin Algayres,
Lucas Ondel,
Laurent Besacier,
Sakriani Sakti,
Emmanuel Dupoux
Publication year - 2020
Publication title -
interspeech 2022
Language(s) - English
Resource type - Conference proceedings
DOI - 10.21437/interspeech.2020-2743
Subject(s) - computer science , speech recognition , word (group theory) , task (project management) , zero (linguistics) , natural language processing , artificial intelligence , representation (politics) , speech analytics , audio mining , quality (philosophy) , resource (disambiguation) , speech synthesis , speech processing , voice activity detection , speech corpus , linguistics , computer network , philosophy , management , epistemology , politics , political science , law , economics
We present the Zero Resource Speech Challenge 2020, which aims at learning speech representations from raw audio signals without any labels. It combines the data sets and metrics from two previous benchmarks (2017 and 2019) and features two tasks which tap into two levels of speech representation. The first task is to discover low bit-rate subword representations that optimize the quality of speech synthesis; the second one is to discover word-like units from unsegmented raw speech. We present the results of the twenty submitted models and discuss the implications of the main findings for unsupervised speech learning.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom