The zero resource speech challenge 2017

By Maarten Versteegh, Roland Thiollière, Thomas Schatz, Xuan-Nga Cao, Xavier Anguera Miró, Aren Jansen, Emmanuel Dupoux. 2017

210 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Speech & Audio

Citations in the corpus

Unsupervised Pretraining Transfers Well Across Languages (2020, methodology): “Trained on ZeroSpeech2017 (45 h) Supervised topline [25] 6.9”
Libri-Light: A Benchmark for ASR with Limited or No Supervision (2019, positive): “The representation is evaluated using ABX error, a distance-based metric used in previous zero resource challenges [9, 10, 11].”
Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019, background): “Evaluation metrics Learning unsupervised speech representations that are indicative of phonetic content is of high interest to the speech community, and recently has been the focus of the ZeroSpeech Challenge (Versteegh et al., 2015; Dunbar et al., 2017; 2019).”
VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019 (2019, background): “In ZeroSpeech 2015 and 2017, the goal was to discover an appropriate speech representation of the underlying language of a dataset [1, 2].”
Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks (2019, neutral): “As part of the 2015 and 2017 Zero Resource Speech Challenges (ZRSC), several unsupervised methods were proposed for learning continuous acoustic representations [6–11].”
A Survey on Neural Speech Synthesis (2021, methodology): “Techniques Data Work Self-supervised Training Unpaired text or speech [51, 368, 433, 78, 140, 346, 197, 352, 71] Cross-lingual Transfer Paired text and speech [42, 390, 12, 60, 271, 105] Cross-speaker Transfer Paired text and speech [216, 125, 59, 39] Speech chain/Back transformation Unpaired text o”
The Zero Resource Speech Challenge 2019: TTS without T (2019, methodology): “Since it is unknown whether the discovered representations correspond to particular linguistic units (phone states, phonemes, features, syllables), we evaluate unit quality with a theory-neutral machine ABX score, as in previous Zero Resource challenges [1, 2].”
UWSpeech: Speech to Speech Translation for Unwritten Languages (2020, background): “Previous works on discrete speech representations include k-means clustering (Kamper, Livescu, and Goldwater 2017; Dunbar et al. 2017), Gaussian mixture model clustering (Chen et al.”
Speech-to-Speech Translation Between Untranscribed Unknown Languages (2019, background): “The Zero Resource Speech Challenge s eries [9, 10, 11] was constructed to progress incrementally toward a system that learns an end-to-end spoken dialog (SD) system in an unknown language from scratch just using information available to language learning infants.”
Data Augmenting Contrastive Learning of Speech Representations in the Time Domain (2020, positive): “This metric has been shown to be useful to analyse the linguistic content of speech features without having to train a classiﬁer [23], and has been used in the Zero Resource Challenge series [9, 10, 24].”
Unsupervised Learning of Semantic Audio Representations (2017, background): “Recent zero-resource efforts in the speech processing community have explicitly aimed to learn meaningful linguistic units from untranscribed speech [14].”
Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner (2016, neutral): “(2009), the unsupervised discovery of phonetic categories is still an unsolved problem in speech technology (see Versteegh, Anguera, Jansen, & Dupoux, 2016; Dunbar et al., 2017).”
Decolonising Speech and Language Technology (2020, background): “, “Systems constructed with zero expert resources [can] help field linguists document endangered languages, by providing tools to semi-automatically analyze and annotate audio recordings using automatically discovered linguistic units” (Dunbar et al., 2017).”
Cyclic Spectral Modeling for Unsupervised Unit Discovery into Voice Conversion with Excitation and Waveform Modeling (2020, background): “Notably, in 2015 [4, 5], 2017 [7], and 2019 [10], the Zero Resource Speech Challenge (ZSC) has been organized, where the objective is to perform the discovery of subword/wordlike speech units (speech sounds representations) without any textual annotations, i.”
Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning (2018, methodology): “Our model is tested in the ABX evaluation of the Zero Resource Speech Challenge - Track 1 [10] and yields a certain improvement over the conventional bottleneck approach [11].”