47 citations · 201 across the 13 of their papers we have counts for
17 papers
Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge
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…
Are word boundaries useful for unsupervised language learning?
Tu Anh Nguyen, Maureen de Seyssel, Robin Algayres +3
Word or word-fragment based Language Models (LM) are typically preferred over character-based ones in many downstream applications. This may not be surprising as words seem more li…
Evaluating context-invariance in unsupervised speech representations
Mark Hallap, Emmanuel Dupoux, Ewan Dunbar
Unsupervised speech representations have taken off, with benchmarks (SUPERB, ZeroSpeech) demonstrating major progress on semi-supervised speech recognition, speech synthesis, and s…
Toward a realistic model of speech processing in the brain with self-supervised learning
Juliette Millet, Charlotte Caucheteux, Pierre Orhan +5
Several deep neural networks have recently been shown to generate activations similar to those of the brain in response to the same input. These algorithms, however, remain largely…
Predicting non-native speech perception using the Perceptual Assimilation Model and state-of-the-art acoustic models
Juliette Millet, Ioana Chitoran, Ewan Dunbar
Our native language influences the way we perceive speech sounds, affecting our ability to discriminate non-native sounds. We compare two ideas about the influence of the native la…
Do self-supervised speech models develop human-like perception biases?
Juliette Millet, Ewan Dunbar
Self-supervised models for speech processing form representational spaces without using any external labels. Increasingly, they appear to be a feasible way of at least partially el…
The Zero Resource Speech Challenge 2021: Spoken language modelling
Ewan Dunbar, Mathieu Bernard, Nicolas Hamilakis +6
We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the…
Paraphrases do not explain word analogies
Louis Fournier, Ewan Dunbar
Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between "jump" and "jumped" will be in a similar direction to tha…
The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé +5
We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource S…
The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
Ewan Dunbar, Julien Karadayi, Mathieu Bernard +6
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 f…
Perceptimatic: A human speech perception benchmark for unsupervised subword modelling
Juliette Millet, Ewan Dunbar
In this paper, we present a data set and methods to compare speech processing models and human behaviour on a phone discrimination task. We provide Perceptimatic, an open data set…
Analogies minus analogy test: measuring regularities in word embeddings
Louis Fournier, Emmanuel Dupoux, Ewan Dunbar
Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim. We decompose an…
The Perceptimatic English Benchmark for Speech Perception Models
Juliette Millet, Ewan Dunbar
We present the Perceptimatic English Benchmark, an open experimental benchmark for evaluating quantitative models of speech perception in English. The benchmark consists of ABX sti…
Independent and automatic evaluation of acoustic-to-articulatory inversion models
Maud Parrot, Juliette Millet, Ewan Dunbar
Reconstruction of articulatory trajectories from the acoustic speech signal has been proposed for improving speech recognition and text-to-speech synthesis. However, to be useful i…
The Zero Resource Speech Challenge 2019: TTS without T
Ewan Dunbar, Robin Algayres, Julien Karadayi +10
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 t…
RNNs Implicitly Implement Tensor Product Representations
R. Thomas McCoy, Tal Linzen, Ewan Dunbar +1
Recurrent neural networks (RNNs) can learn continuous vector representations of symbolic structures such as sequences and sentences; these representations often exhibit linear regu…
Learning weakly supervised multimodal phoneme embeddings
Rahma Chaabouni, Ewan Dunbar, Neil Zeghidour +1
Recent works have explored deep architectures for learning multimodal speech representation (e.g. audio and images, articulation and audio) in a supervised way. Here we investigate…