相关论文: Audio ALBERT: A Lite BERT for Self-supervised Lear…

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to…

Self-supervised learning has been used to leverage unlabelled data, improving accuracy and generalisation of speech systems through the training of representation models. While many recent works have sought to produce effective…

Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply…

Recent years have witnessed significant improvement in ASR systems to recognize spoken utterances. However, it is still a challenging task for noisy and out-of-domain data, where substitution and deletion errors are prevalent in the…

Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success…

We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given…

Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…

Self-supervised speech representation learning has shown promising results in various speech processing tasks. However, the pre-trained models, e.g., HuBERT, are storage-intensive Transformers, limiting their scope of applications under…

Recently developed large pre-trained language models, e.g., BERT, have achieved remarkable performance in many downstream natural language processing applications. These pre-trained language models often contain hundreds of millions of…

Textless self-supervised speech models have grown in capabilities in recent years, but the nature of the linguistic information they encode has not yet been thoroughly examined. We evaluate the extent to which these models' learned…

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…

Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase,…

Self-supervised models have had great success in learning speech representations that can generalize to various downstream tasks. However, most self-supervised models require a large amount of compute and multiple GPUs to train,…

We introduce BERTphone, a Transformer encoder trained on large speech corpora that outputs phonetically-aware contextual representation vectors that can be used for both speaker and language recognition. This is accomplished by training on…

Self-supervised pre-trained speech models were shown effective for various downstream speech processing tasks. Since they are mainly pre-trained to map input speech to pseudo-labels, the resulting representations are only effective for the…

Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…

We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts,…

Fine-tuned Bidirectional Encoder Representations from Transformers (BERT)-based sequence classification models have proven to be effective for detecting Alzheimer's Disease (AD) from transcripts of human speech. However, previous research…

Audio captioning aims at using natural language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture, in which acoustic information is extracted by an audio…