Unsupervised Learning of Acoustic Sub-word Units

Accurate unsupervised learning of phonemes of a language directly from speech is demonstrated via an algorithm for joint unsupervised learning of the topology and parameters of a hidden Markov model (HMM); states and short state-sequences through this HMM correspond to the learnt sub-word units. The algorithm, originally proposed for unsupervised learning of allophonic variations within a given phoneme set, has been adapted to learn without any knowledge of the phonemes. An evaluation methodology is also proposed, whereby the state-sequence that aligns to a test utterance is transduced in an automatic manner to a phoneme-sequence and compared to its manual transcription. Over 85% phoneme recognition accuracy is demonstrated for speaker-dependent learning from fluent, large-vocabulary speech. 1 Automatic Discovery of Phone(me)s Statistical models learnt from data are extensively used in modern automatic speech recognition (ASR) systems. Transcribed speech is used to estimate conditiona...

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Balakrishnan Varadarajan, Sanjeev Khudanpur, Emmanuel Dupoux
• Keywords: Accurate Unsupervised Learning, ACL 2008, Computational Linguistics, Joint Unsupervised Learning, Unsupervised Learning