Attention model for articulatory features detection

Code

• github.com/sciforce/phones-las
  OfficialIn papertf★ 33

Abstract

Articulatory distinctive features, as well as phonetic transcription, play important role in speech-related tasks: computer-assisted pronunciation training, text-to-speech conversion (TTS), studying speech production mechanisms, speech recognition for low-resourced languages. End-to-end approaches to speech-related tasks got a lot of traction in recent years. We apply Listen, Attend and Spell~(LAS)~Chan-LAS2016 architecture to phones recognition on a small small training set, like TIMIT~TIMIT-1992. Also, we introduce a novel decoding technique that allows to train manners and places of articulation detectors end-to-end using attention models. We also explore joint phones recognition and articulatory features detection in multitask learning setting.

Tasks

Benchmark Results

Reproductions