paper-with-me

Papers

The Zero Resource Speech Challenge 2017

2017-12-12 · Ewan Dunbar, Xuan Nga Cao, Juan Benjumea, Julien Karadayi, Mathieu Bernard, Laurent Besacier, Xavier Anguera, Emmanuel Dupoux

We describe a new challenge aimed at discovering subword and word units from raw speech. This challenge is the followup to the Zero Resource Speech Challenge 2015. It aims at constructing systems that generalize across languages and adapt to new speakers. The design features and evaluation metrics of the challenge are presented and the results of seventeen models are discussed.

📄 PDF Abstract BibTeX arXiv:1712.04313

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition

2021-07-14 · Afra Alishahia, Grzegorz Chrupała, Alejandrina Cristia, Emmanuel Dupoux 외

We present the visually-grounded language modelling track that was introduced in the Zero-Resource Speech challenge, 2021 edition, 2nd round. We motivate the new track and discuss participation rules in detail. We also p…

Language Modelling

The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units

2020-10-12 · Ewan Dunbar, Julien Karadayi, Mathieu Bernard, Xuan-Nga Cao 외

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 20…

Speech Synthesis

Multilingual acoustic word embeddings for zero-resource languages

2024-01-19 · Christiaan Jacobs

This research addresses the challenge of developing speech applications for zero-resource languages that lack labelled data. It specifically uses acoustic word embedding (AWE) -- fixed-dimensional representations of vari…

Hate Speech DetectionKeyword SpottingWord Embeddings

Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge

2022-10-27 · Ewan Dunbar, Nicolas Hamilakis, Emmanuel Dupoux

Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as…

Acoustic Unit DiscoveryLanguage ModelingLanguage ModellingResynthesis

The Zero Resource Speech Challenge 2019: TTS without T

2019-04-25 · Ewan Dunbar, Robin Algayres, Julien Karadayi, Mathieu Bernard 외

We present the Zero Resource Speech Challenge 2019, which proposes to build a speech synthesizer without any text or phonetic labels: hence, TTS without T (text-to-speech without text). We provide raw audio for a target …

text-to-speechText to Speech