3 accepted papers
Unlike modern streaming Automatic Speech Recognition (ASR) systems which segment speech into fixed-length chunks for decoding, humans perceive speech in variable-length units of information. This paper proposes a novel method that leverages self-information, a measure of the information contained wi…
This paper introduces CIF-RNNT, a model that incorporates Continuous Integrate-and-Fire into RNN-Transducers (RNNTs) for streaming ASR via acoustic word embeddings (AWEs). CIF can dynamically compress long sequences into shorter ones, while RNNTs can produce multiple symbols given an input vector. W…
In this paper, we present a voice conversion (VC) method that does not use any parallel data while training the model. VC is a technique where only speaker specific information in source speech is converted while keeping the phonological information unchanged. Most of the existing VC methods rely on…