Related papers: Probing self-attention in self-supervised speech m…

In aspect-based sentiment analysis (ABSA), many neural models are equipped with an attention mechanism to quantify the contribution of each context word to sentiment prediction. However, such a mechanism suffers from one drawback: only a…

Speech to text models tend to be trained and evaluated against a single target accent. This is especially true for English for which native speakers from the United States became the main benchmark. In this work, we are going to show how…

Transformer-based Neural Language Models achieve state-of-the-art performance on various natural language processing tasks. However, an open question is the extent to which these models rely on word-order/syntactic or word…

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents.…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Continual pretraining is a popular way of building a domain-specific pretrained language model from a general-domain language model. In spite of its high efficiency, continual pretraining suffers from catastrophic forgetting, which may harm…

The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows…

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…

Transformers have achieved state-of-the-art performance in morphological inflection tasks, yet their ability to generalize across languages and morphological rules remains limited. One possible explanation for this behavior can be the…

Transformer based pre-trained models such as BERT and its variants, which are trained on large corpora, have demonstrated tremendous success for natural language processing (NLP) tasks. Most of academic works are based on the English…

Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers. Applying these approaches to Automatic Speech Recognition, we demonstrate…

Recognizing emotions from speech using machine learning has become an active research area due to its importance in building human-centered applications. However, while many studies have been conducted in English, German, and other European…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better…

We present the first unified study of the efficiency of self-attention-based Transformer variants spanning text, speech and vision. We identify input length thresholds (tipping points) at which efficient Transformer variants become more…

In this paper, we present a novel approach to developing an English Automatic Speech Recognition (ASR) system that can effectively handle Hindi queries, without compromising its performance on English. We propose a novel acoustic model…

We introduce exclusive self attention (XSA), a simple modification of self attention (SA) that improves Transformer's sequence modeling performance. The key idea is to constrain attention to capture only information orthogonal to the…

Recent Transformer-based large-scale pre-trained models have revolutionized vision-and-language (V+L) research. Models such as ViLBERT, LXMERT and UNITER have significantly lifted state of the art across a wide range of V+L benchmarks with…

This paper presents a novel open-domain dialogue generation model emphasizing the differentiation of speakers in multi-turn conversations. Differing from prior work that solely relies on the content of conversation history to generate a…