Related papers: BEST-RQ-Based Self-Supervised Learning for Whisper…
Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…
Overlapping speech diarization has been traditionally treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding multiple binary labels into a single label with…
Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is important for self-supervised learning. We propose a simple…
Although automatic speech recognition (ASR) task has gained remarkable success by sequence-to-sequence models, there are two main mismatches between its training and testing that might lead to performance degradation: 1) The typically used…
Test-Time Adaptation (TTA) via entropy minimization (EM) has proven effective for classification tasks, yet its application to generative autoregressive models remains theoretically fragmented. Existing approaches typically rely on distinct…
Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific…
Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to…
Reading comprehension (RC) has been studied in a variety of datasets with the boosted performance brought by deep neural networks. However, the generalization capability of these models across different domains remains unclear. To alleviate…
Personalizing automatic speech recognition (ASR) systems for non-normative speech, such as dysarthric and aphasic speech, is challenging. While speaker-specific fine-tuning (SS-FT) is widely used, it is typically initialized directly from a…
Automatic speech recognition (ASR) models with low-footprint are increasingly being deployed on edge devices for conversational agents, which enhances privacy. We study the problem of federated continual incremental learning for recurrent…
Test-Time Adaptation (TTA) has emerged as a crucial solution to the domain shift challenge, wherein the target environment diverges from the original training environment. A prime exemplification is TTA for Automatic Speech Recognition…
Building an automatic speech recognition (ASR) system from scratch requires a large amount of annotated speech data, which is difficult to collect in many languages. However, there are cases where the low-resource language shares a common…
Teacher-student (T/S) has shown to be effective for domain adaptation of deep neural network acoustic models in hybrid speech recognition systems. In this work, we extend the T/S learning to large-scale unsupervised domain adaptation of an…
ASR systems designed for native English (L1) usually underperform on non-native English (L2). To address this performance gap, \textbf{(i)} we extend our previous work to investigate fine-tuning of a pre-trained wav2vec 2.0 model…
In this paper, we propose a language-universal adapter learning framework based on a pre-trained model for end-to-end multilingual automatic speech recognition (ASR). For acoustic modeling, the wav2vec 2.0 pre-trained model is fine-tuned by…
We propose a self-speaker adaptation method for streaming multi-talker automatic speech recognition (ASR) that eliminates the need for explicit speaker queries. Unlike conventional approaches requiring target speaker embeddings or…
We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…
Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…
The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show that self-training is…
Automatic speech recognition (ASR) training can utilize multiple experts as teacher models, each trained on a specific domain or accent. Teacher models may be opaque in nature since their architecture may be not be known or their training…