Emmanuel Dupoux

A Temporal Coherence Loss Function for Learning Unsupervised Acoustic Embeddings

2016 · Procedia Computer Science

We train neural networks of varying depth with a loss function which imposes the output representations to have a temporal profile which looks like that of phonemes. We show that a simple loss function which …

The Zero Resource Speech Challenge 2019: TTS Without T

2019

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

Textless Speech Emotion Conversion using Discrete & Decomposed Representations

2022

Felix Kreuk, Adam Polyak, Jade Copet, Eugene Kharitonov, Tu Anh Nguyen, Morgan Rivière, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux, Yossi Adi. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

The Zero Resource Speech Challenge 2015: Proposed Approaches and Results

2016 · Procedia Computer Science

This paper reports on the results of the Zero Resource Speech Challenge 2015, the first unified benchmark for zero resource speech technology, which aims at the unsupervised discovery of subword and word units from raw …

Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies

2016 · Transactions of the Association for Computational Linguistics

The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Linguistic regularities are often sensitive to syntactic structure; can such dependencies be …

The zero resource speech challenge 2015

2015

établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Libri-Light: A Benchmark for ASR with Limited or No Supervision

2020

We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K …