We introduce a new collection of spoken English audio suitable for training speech
recognition systems under limited or no supervision. It is derived from open-source audio …

We propose to learn a low-dimensional feature representation for multiple languages
without access to their manual transcription. The multilingual features are extracted from a …

Today we can find many use cases for content-based speech classification. These include
speech topic identification and spoken command recognition. Automatic Speech …

Modern topic identification (topic ID) systems for speech use automatic speech recognition
(ASR) to produce speech transcripts, and perform supervised classification on such ASR …

Automatic speech recognition (ASR) systems often need to be developed for extremely low-
resource languages to serve end-uses such as audio content categorization and search …

We propose a novel technique that learns a low-dimensional feature representation from
unlabeled data of a target language, and labeled data from a nontarget language. The …

We present a method enabling the unsupervised discovery of sub-word units (SWUs) and
associated pronunciation lexicons for use in automatic speech recognition (ASR) systems …

Unsupervised term discovery is the task of identifying and grouping reoccurring word-like
patterns from the untranscribed audio data. It facilitates unsupervised acoustic model …

We experiment with unsupervised methods for deriving and clustering symbolic
representations of speech, working towards speech-to-speech translation for languages …

In this contribution we show how to exploit text data to support word discovery from audio
input in an underresourced target language. Given audio, of which a certain amount is …