Related papers: Analysis of Predictive Coding Models for Phonemic …

Predictive coding (PC) is an influential theory in computational neuroscience, which argues that the cortex forms unsupervised world models by implementing a hierarchical process of prediction error minimization. PC networks (PCNs) are…

We present a bidirectional unsupervised model pre-training (UPT) method and apply it to children's automatic speech recognition (ASR). An obstacle to improving child ASR is the scarcity of child speech databases. A common approach to…

Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to…

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby coupling the model to that compressor. This work introduces…

Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we present ContraCLM, a novel contrastive learning framework at both…

The increasingly stringent requirement on quality-of-experience in 5G/B5G communication systems has led to the emerging neural speech enhancement techniques, which however have been developed in isolation from the existing expert-rule based…

We propose a method named AudioFormer,which learns audio feature representations through the acquisition of discrete acoustic codes and subsequently fine-tunes them for audio classification tasks. Initially,we introduce a novel perspective…

Predictive coding (PC) networks are a biologically interesting class of neural networks. Their layered hierarchy mimics the reciprocal connectivity pattern observed in the mammalian cortex, and they can be trained using local learning rules…

Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of…

Most spoken language understanding systems use a pipeline approach composed of an automatic speech recognition interface and a natural language understanding module. This approach forces hard decisions when converting continuous inputs into…

We propose an end-to-end learned image compression codec wherein the analysis transform is jointly trained with an object classification task. This study affirms that the compressed latent representation can predict human perceptual…

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…

Autoregressive neural network models have been used successfully for sequence generation, feature extraction, and hypothesis scoring. This paper presents yet another use for these models: allocating more computation to more difficult…

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…

Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level…

Language identification from speech is a common preprocessing step in many spoken language processing systems. In recent years, this field has seen fast progress, mostly due to the use of self-supervised models pretrained on multilingual…

Linguistic features have shown promising applications for detecting various cognitive impairments. To improve detection accuracies, increasing the amount of data or the number of linguistic features have been two applicable approaches.…

Phoneme boundary detection plays an essential first step for a variety of speech processing applications such as speaker diarization, speech science, keyword spotting, etc. In this work, we propose a neural architecture coupled with a…

Recently, phonetic posteriorgrams (PPGs) based methods have been quite popular in non-parallel singing voice conversion systems. However, due to the lack of acoustic information in PPGs, style and naturalness of the converted singing voices…