相关论文: MCR-Data2vec 2.0: Improving Self-supervised Speech…

Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch architecture for preventing collapse and stabilizing the…

Continuous unsupervised representation learning (CURL) research has greatly benefited from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL methods using SSL can learn high-quality representations…

Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep models overfitting remains the largest problem, outweighing performance improvements…

In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data.…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

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…

Consistency regularization has been widely studied in recent semisupervised semantic segmentation methods, and promising performance has been achieved. In this work, we propose a new consistency regularization framework, termed mutual…

With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream tasks. However, we find that current SSL models suffer severe…

Self-supervised learning (SSL) has achieved great success in speech-related tasks. While Transformer and Conformer architectures have dominated SSL backbones, encoders like Zipformer, which excel in automatic speech recognition (ASR),…

Effective suppression of surface-related multiples is essential to prevent imaging artifacts and erroneous structural interpretations. While conventional approaches rely on accurate priors or subsurface model knowledge, and supervised…

Self-supervised learning (SSL) on large-scale datasets like AudioSet has become the dominant paradigm for audio representation learning. While the continuous influx of new, unlabeled audio presents an opportunity to enrich these static…

Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech…

Predicting the altered acoustic frames is an effective way of self-supervised learning for speech representation. However, it is challenging to prevent the pretrained model from overfitting. In this paper, we proposed to introduce two…

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a…

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

Audio-visual automatic speech recognition (AV-ASR) models are very effective at reducing word error rates on noisy speech, but require large amounts of transcribed AV training data. Recently, audio-visual self-supervised learning (SSL)…

We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream…

We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In…

Semi-supervised learning (SSL) is an active area of research which aims to utilize unlabelled data in order to improve the accuracy of speech recognition systems. The current study proposes a methodology for integration of two key ideas: 1)…