LibriSpeech

AbstractThe multi-level adaptive networks (MLAN) technique is a cross-lingual adaptation framework where a bottleneck (BN) layer in a deep neural network (DNN) trained in a source language is used for …...

Recent works in spoken language translation (SLT) have attempted to build end-to-end speech-to-text translation without using source language transcription during learning or decoding. However, while large quantities of parallel texts …...

AbstractFor automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then trans- late with machine translation (MT). A major cause of …...

AbstractInformation in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features. In this paper, we …...

AbstractUnsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on evaluating …...

AbstractNon-autoregressive encoder-decoder models greatly improve decoding speed over autoregressive models, at the expense of generation quality. To mitigate this, iterative decoding models repeatedly infill or refine the proposal of a …...

AbstractASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually use text-based input, comprised solely …...