The Zero Resource Speech Challenge 2019: TTS Without T

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 an\nunknown language (the Voice dataset), but no alignment, text or labels.\nParticipants must discover subword units in an unsupervised way (using the Unit\nDiscovery dataset) and align them to the voice recordings in a way that works\nbest for the purpose of synthesizing novel utterances from novel speakers,\nsimilar to the target speaker's voice. We describe the metrics used for\nevaluation, a baseline system consisting of unsupervised subword unit discovery\nplus a standard TTS system, and a topline TTS using gold phoneme\ntranscriptions. We present an overview of the 19 submitted systems from 10\nteams and discuss the main results.\n