Libri-light: A benchmark for asr with limited or no supervision
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 …
recognition systems under limited or no supervision. It is derived from open-source audio …
Multilingual bottle-neck feature learning from untranscribed speech
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 …
without access to their manual transcription. The multilingual features are extracted from a …
Sinhala and tamil speech intent identification from english phoneme based asr
Y Karunanayake, U Thayasivam… - … Conference on Asian …, 2019 - ieeexplore.ieee.org
Today we can find many use cases for content-based speech classification. These include
speech topic identification and spoken command recognition. Automatic Speech …
speech topic identification and spoken command recognition. Automatic Speech …
Topic identification for speech without asr
Modern topic identification (topic ID) systems for speech use automatic speech recognition
(ASR) to produce speech transcripts, and perform supervised classification on such ASR …
(ASR) to produce speech transcripts, and perform supervised classification on such ASR …
Automatic speech recognition and topic identification for almost-zero-resource languages
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 …
resource languages to serve end-uses such as audio content categorization and search …
Multitask feature learning for low-resource query-by-example spoken term detection
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 …
unlabeled data of a target language, and labeled data from a nontarget language. The …
Automatic sub-word unit discovery and pronunciation lexicon induction for ASR with application to under-resourced languages
W Agenbag, T Niesler - Computer Speech & Language, 2019 - Elsevier
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 …
associated pronunciation lexicons for use in automatic speech recognition (ASR) systems …
Bottom-up unsupervised word discovery via acoustic units
Unsupervised term discovery is the task of identifying and grouping reoccurring word-like
patterns from the untranscribed audio data. It facilitates unsupervised acoustic model …
patterns from the untranscribed audio data. It facilitates unsupervised acoustic model …
[PDF][PDF] Unsupervised Phonetic and Word Level Discovery for Speech to Speech Translation for Unwritten Languages.
We experiment with unsupervised methods for deriving and clustering symbolic
representations of speech, working towards speech-to-speech translation for languages …
representations of speech, working towards speech-to-speech translation for languages …
[PDF][PDF] Leveraging text data for word segmentation for underresourced 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 …
input in an underresourced target language. Given audio, of which a certain amount is …