Essays about: "unsupervised acoustic modelling"
Found 2 essays containing the words unsupervised acoustic modelling.
-
1. Speaker Recognition using Biology-Inspired Feature Extraction
University essay from Lunds universitet/Institutionen för elektro- och informationsteknikAbstract : Distinguishing between people's voices is something the human brain does naturally, using only frequencies picked up by the inner ear. The field of speaker recognition is concerned with making machines do the same thing using digitally sampled speech and data processing. READ MORE
-
2. Increasing speaker invariance in unsupervised speech learning by partitioning probabilistic models using linear siamese networks
University essay from KTH/Tal, musik och hörsel, TMHAbstract : Unsupervised learning of speech is concerned with automatically finding patterns such as words or speech sounds, without supervision in the form of orthographical transcriptions or a priori knowledge of the language. However, a fundamental problem is that unsupervised speech learning methods tend to discover highly speaker-specific and context-dependent representations of speech. READ MORE