Related papers: Hierarchical Multi Task Learning With CTC

Modern ASR systems are typically trained on large-scale pseudo-labeled, in-the-wild data spanning multiple domains. While such heterogeneous data benefit generalist models designed for broad deployment, they pose challenges for specialist…

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for…

In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised…

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by…

Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work…

We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly…

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English…

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…

Low-resource speech recognition has been long-suffering from insufficient training data. In this paper, we propose an approach that leverages neighboring languages to improve low-resource scenario performance, founded on the hypothesis that…

In this paper, we frame homogeneous-feature multi-task learning (MTL) as a hierarchical representation learning problem, with one task-agnostic and multiple task-specific latent representations. Drawing inspiration from the information…

Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of…

Token representations in high-dimensional latent spaces often exhibit redundancy, limiting computational efficiency and reducing structural coherence across model layers. Hierarchical latent space folding introduces a structured…

Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation model along with an auxiliary text to text translation task.…

Recent advances in language modeling and vision stem from training large models on diverse, multi-task data. This paradigm has had limited impact in value-based reinforcement learning (RL), where improvements are often driven by small…

Multi-human multi-robot teams (MH-MR) obtain tremendous potential in tackling intricate and massive missions by merging distinct strengths and expertise of individual members. The inherent heterogeneity of these teams necessitates advanced…

Representation learning is a widely adopted framework for learning in data-scarce environments, aiming to extract common features from related tasks. While centralized approaches have been extensively studied, decentralized methods remain…

Large-scale EHR prediction across institutions is hindered by substantial heterogeneity in schemas and code systems. Although Common Data Models (CDMs) can standardize records for multi-institutional learning, the manual harmonization and…

State-of-the-art approaches to spelling error correction problem include Transformer-based Seq2Seq models, which require large training sets and suffer from slow inference time; and sequence labeling models based on Transformer encoders…

The performance of most emotion recognition systems degrades in real-life situations ('in the wild' scenarios) where the audio is contaminated by reverberation. Our study explores new methods to alleviate the performance degradation of SER…