相关论文: Categorize Early, Integrate Late: Divergent Proces…

Identification of cognates across related languages is one of the primary problems in historical linguistics. Automated cognate identification is helpful for several downstream tasks including identifying sound correspondences,…

This work builds together two popular blocks of neural architecture, namely convolutional layers and Transformers, for large language models (LLMs). Non-causal conformers are used ubiquitously in automatic speech recognition. This work aims…

This article surveys convolution-based models including convolutional neural networks (CNNs), Conformers, ResNets, and CRNNs-as speech signal processing models and provide their statistical backgrounds and speech recognition, speaker…

We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…

Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing…

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Paralinguistic speech processing is important in addressing many issues, such as sentiment and neurocognitive disorder analyses. Recently, Transformer has achieved remarkable success in the natural language processing field and has…

After their successful debut in natural language processing, Transformer architectures are now becoming the de-facto standard in many domains. An obstacle for their deployment over new modalities is the architectural configuration: the…

We present a system for the Zero Resource Speech Challenge 2021, which combines a Contrastive Predictive Coding (CPC) with deep cluster. In deep cluster, we first prepare pseudo-labels obtained by clustering the outputs of a CPC network…

Pretrained self-supervised speech models excel in speech tasks but do not reflect the hierarchy of human speech processing, as they encode rich semantics in middle layers and poor semantics in late layers. Recent work showed that…

Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations…

Conformer has achieved impressive results in Automatic Speech Recognition (ASR) by leveraging transformer's capturing of content-based global interactions and convolutional neural network's exploiting of local features. In Conformer, two…

Over the past two decades, CNN architectures have produced compelling models of sound perception and cognition, learning hierarchical organizations of features. Analogous to successes in computer vision, audio feature classification can be…

The use of deep pre-trained bidirectional transformers has led to remarkable progress in a number of applications (Devlin et al., 2018). For tasks that make pairwise comparisons between sequences, matching a given input with a corresponding…

Recently, fine-tuning large pre-trained Transformer models using downstream datasets has received a rising interest. Despite their success, it is still challenging to disentangle the benefits of large-scale datasets and Transformer…

Neural network architectures designed for function parameterization, such as the Bag-of-Functions (BoF) framework, bridge the gap between the expressivity of deep learning and the interpretability of classical signal processing. However,…

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…

Transformers underlie almost all state-of-the-art language models in computational linguistics, yet their cognitive adequacy as models of human sentence processing remains disputed. In this work, we use a surprisal-based linking mechanism…

Conformer, a convolution-augmented Transformer variant, has become the de facto encoder architecture for speech processing due to its superior performance in various tasks, including automatic speech recognition (ASR), speech translation…

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…