5 papers
A Corpus for Large-Scale Phonetic Typology
Elizabeth Salesky, Eleanor Chodroff, Tiago Pimentel +4
A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions. We present VoxClamantis v1.0, the first large-scale c…
Induced Inflection-Set Keyword Search in Speech
Oliver Adams, Matthew Wiesner, Jan Trmal +2
We investigate the problem of searching for a lexeme-set in speech by searching for its inflectional variants. Experimental results indicate how lexeme-set search performance chang…
Massively Multilingual Adversarial Speech Recognition
Oliver Adams, Matthew Wiesner, Shinji Watanabe +1
We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity b…
Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings
Matthew Wiesner, Adithya Renduchintala, Shinji Watanabe +3
We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because t…
Analysis of Multilingual Sequence-to-Sequence speech recognition systems
Martin Karafiát, Murali Karthick Baskar, Shinji Watanabe +3
This paper investigates the applications of various multilingual approaches developed in conventional hidden Markov model (HMM) systems to sequence-to-sequence (seq2seq) automatic…