相关论文: Pre-trained Model Representations and their Robust…

We propose a novel transfer learning method for speech emotion recognition allowing us to obtain promising results when only few training data is available. With as low as 125 examples per emotion class, we were able to reach a higher…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

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…

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…

Audio-visual pre-trained models have gained substantial attention recently and demonstrated superior performance on various audio-visual tasks. This study investigates whether pre-trained audio-visual models demonstrate non-arbitrary…

Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to…

Advancements in monaural speech enhancement (SE) techniques have greatly improved the perceptual quality of speech. However, integrating these techniques into automatic speech recognition (ASR) systems has not yielded the expected…

In automatic speech recognition, often little training data is available for specific challenging tasks, but training of state-of-the-art automatic speech recognition systems requires large amounts of annotated speech. To address this…

While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…

Recently, a variational autoencoder (VAE)-based single-channel speech enhancement system using Bayesian permutation training has been proposed, which uses two pretrained VAEs to obtain latent representations for speech and noise. Based on…

Recent studies have explored the use of pre-trained embeddings for speech emotion recognition (SER), achieving comparable performance to conventional methods that rely on low-level knowledge-inspired acoustic features. These embeddings are…

Cross-lingual self-supervised learning has been a growing research topic in the last few years. However, current works only explored the use of audio signals to create representations. In this work, we study cross-lingual self-supervised…

Speech representation models based on the transformer architecture and trained by self-supervised learning have shown great promise for solving tasks such as speech and speaker recognition, keyword spotting, emotion detection, and more.…

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

We propose a novel multi-task pre-training method for Speech Emotion Recognition (SER). We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more…

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

Leveraging context information is an intuitive idea to improve performance on conversational automatic speech recognition(ASR). Previous works usually adopt recognized hypotheses of historical utterances as preceding context, which may bias…

Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…

Large, self-supervised transformer-based language representation models have recently received significant amounts of attention, and have produced state-of-the-art results across a variety of tasks simply by scaling up pre-training on…

In this paper we introduce a new natural language processing dataset and benchmark for predicting prosodic prominence from written text. To our knowledge this will be the largest publicly available dataset with prosodic labels. We describe…