Neural networks : the official journal of the International Neural Network Society
May 25, 2021
Convolutional neural network (CNN) based methods, such as the convolutional encoder-decoder network, offer state-of-the-art results in monaural speech enhancement. In the conventional encoder-decoder network, large kernel size is often used to enhanc...
Neural networks : the official journal of the International Neural Network Society
May 17, 2021
The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. Nowadays, state-of-the-art ST systems are populated with deep neural ...
Neural networks : the official journal of the International Neural Network Society
May 14, 2021
Traditionally, learning speech synthesis and speech recognition were investigated as two separate tasks. This separation hinders incremental development for concurrent synthesis and recognition, where partially-learned synthesis and partially-learned...
Neural networks : the official journal of the International Neural Network Society
May 14, 2021
We introduce the novel concept of anti-transfer learning for speech processing with convolutional neural networks. While transfer learning assumes that the learning process for a target task will benefit from re-using representations learned for anot...
Neural networks : the official journal of the International Neural Network Society
Apr 21, 2021
Significant progress has recently been made in speaker diarisation after the introduction of d-vectors as speaker embeddings extracted from neural network (NN) speaker classifiers for clustering speech segments. To extract better-performing and more ...
Neural networks : the official journal of the International Neural Network Society
Apr 21, 2021
Deep attractor networks (DANs) perform speech separation with discriminative embeddings and speaker attractors. Compared with methods based on the permutation invariant training (PIT), DANs define a deep embedding space and deliver a more elaborate r...
Neural networks : the official journal of the International Neural Network Society
Apr 19, 2021
The traditional generalized sidelobe canceller (GSC) is a common speech enhancement front end to improve the noise robustness of automatic speech recognition (ASR) systems in the far-field cases. However, the traditional GSC is optimized based on the...
Topics in cognitive science
Apr 9, 2021
Contemporary psycholinguistic models place significant emphasis on the cognitive processes involved in the acquisition, recognition, and production of language but neglect many issues related to the representation of language-related information in t...
Computational intelligence and neuroscience
Apr 8, 2021
Loanword identification is studied in recent years to alleviate data sparseness in several natural language processing (NLP) tasks, such as machine translation, cross-lingual information retrieval, and so on. However, recent studies on this topic usu...
Neural networks : the official journal of the International Neural Network Society
Apr 5, 2021
Respiration is an essential and primary mechanism for speech production. We first inhale and then produce speech while exhaling. When we run out of breath, we stop speaking and inhale. Though this process is involuntary, speech production involves a ...