The Zero Resource Speech Challenge 2020: Discovering Discrete Subword And Word Units

Abstract

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.

Stats

• citations34
• S2 citations—
• github stars0
• HF likes0
• heat score11.58
• arxiv keydunbar2020the

Related papers

• Self-supervised Language Learning From Raw Audio: Lessons From The Zero Resource Speech Challenge (2022)10.07
• The Zero Resource Speech Challenge 2019: TTS Without T (2019)13.17
• The Zero Resource Speech Benchmark 2021: Metrics And Baselines For Unsupervised Spoken Language Modeling (2020)0.00
• Information Retrieval For Zerospeech 2021: The Submission By University Of Wroclaw (2021)7.81
• Combining Adversarial Training And Disentangled Speech Representation For Robust Zero-resource Subword Modeling (2019)7.16
• Exploration Of End-to-end Synthesisers Forzero Resource Speech Challenge 2020 (2020)4.52
• Transformer VQ-VAE For Unsupervised Unit Discovery And Speech Synthesis: Zerospeech 2020 Challenge (2020)9.41
• Multilingual And Unsupervised Subword Modeling For Zero-resource Languages (2018)7.81