Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

In the last decade, deep supervised learning has had tremendous success. However, its
flaws, such as its dependency on manual and costly annotations on large datasets and …

Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been
extensively investigated in the supervised setting. This assumes the existence of a parallel …

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 …

Contrastive Predictive Coding (CPC), based on predicting future segments of speech from
past segments is emerging as a powerful algorithm for representation learning of speech …

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 …

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 …

Abstract Automatic Speech Recognition (ASR) systems can be trained to achieve
remarkable performance given large amounts of manually transcribed speech, but large …

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 …

We describe our submitted system for the ZeroSpeech Challenge 2019. The current
challenge theme addresses the difficulty of constructing a speech synthesizer without any …