3 papers
eess.AS2020
Improving Unsupervised Sparsespeech Acoustic Models with Categorical Reparameterization
Benjamin Milde, Chris Biemann
The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling o…
cs.CL2018
Open Source Automatic Speech Recognition for German
Benjamin Milde, Arne Köhn
High quality Automatic Speech Recognition (ASR) is a prerequisite for speech-based applications and research. While state-of-the-art ASR software is freely available, the language…
cs.SD2018
Unspeech: Unsupervised Speech Context Embeddings
Benjamin Milde, Chris Biemann
We introduce "Unspeech" embeddings, which are based on unsupervised learning of context feature representations for spoken language. The embeddings were trained on up to 9500 hours…