相关论文: An Exploration into the Performance of Unsupervise…

Large self-supervised pre-trained speech models have achieved remarkable success across various speech-processing tasks. The self-supervised training of these models leads to universal speech representations that can be used for different…

Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech data and then used for a range of downstream tasks. These models use a masked prediction objective, where the model learns to…

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…

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…

We investigate robustness properties of pre-trained neural models for automatic speech recognition. Real life data in machine learning is usually very noisy and almost never clean, which can be attributed to various factors depending on the…

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,…

Modern neural speech models benefit from having longer context, and many approaches have been proposed to increase the maximum context a model can use. However, few have attempted to measure how much context these models actually use, i.e.,…

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…

Representations derived from models such as BERT (Bidirectional Encoder Representations from Transformers) and HuBERT (Hidden units BERT), have helped to achieve state-of-the-art performance in dimensional speech emotion recognition.…

Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition…

Speech modeling methods learn one embedding for a fixed segment of speech, typically in between 10-25 ms. The information present in speech can be divided into two categories: "what is being said" (content) and "how it is expressed" (other)…

Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such representations may be skewed toward canonical data…

Self-supervised learning has shown great success in Speech Recognition. However, it has been observed that finetuning all layers of the learned model leads to lower performance compared to resetting top layers. This phenomenon is attributed…

Pre-trained model representations have demonstrated state-of-the-art performance in speech recognition, natural language processing, and other applications. Speech models, such as Bidirectional Encoder Representations from Transformers…

Recent innovations in self-supervised representation learning have led to remarkable advances in natural language processing. That said, in the speech processing domain, self-supervised representation learning-based systems are not yet…

Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored. We study the transfer learning capabilities of such models on bioacoustic…

Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language…

While audio-visual speech models can yield superior performance and robustness compared to audio-only models, their development and adoption are hindered by the lack of labeled and unlabeled audio-visual data and the cost to deploy one…

This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a…

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…