Related papers: Transducer Consistency Regularization for Speech t…

Numerous diffusion model (DM)-based methods have been proposed for solving inverse imaging problems. Among these, a recent line of work has demonstrated strong performance by formulating sampling as an optimization procedure that enforces…

Simultaneous translation systems start producing the output while processing the partial source sentence in the incoming input stream. These systems need to decide when to read more input and when to write the output. These decisions depend…

Online speech recognition is crucial for developing natural human-machine interfaces. This modality, however, is significantly more challenging than off-line ASR, since real-time/low-latency constraints inevitably hinder the use of future…

End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language models have to be retrained whenever the corpus of interest changes. Furthermore,…

Text generation models are notoriously vulnerable to errors in the training data. With the wide-spread availability of massive amounts of web-crawled data becoming more commonplace, how can we enhance the robustness of models trained on a…

It's challenging to customize transducer-based automatic speech recognition (ASR) system with context information which is dynamic and unavailable during model training. In this work, we introduce a light-weight contextual spelling…

This paper presents a novel optimization framework for automatic speech recognition (ASR) with the aim of reducing hallucinations produced by an ASR model. The proposed framework optimizes the ASR model to maximize an expected factual…

This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w.r.t. to the language model. This takes advantage of the fact that if the language model will reliably and accurately predict a token…

Semi-supervised domain adaptation (SSDA) has been extensively researched due to its ability to improve classification performance and generalization ability of models by using a small amount of labeled data on the target domain. However,…

Noise robustness in keyword spotting remains a challenge as many models fail to overcome the heavy influence of noises, causing the deterioration of the quality of feature embeddings. We proposed a contrastive regularization method called…

Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is more essential to…

Recommender systems (RecSys) have become essential in modern society, driving user engagement and satisfaction across diverse online platforms. Most RecSys focuses on designing a powerful encoder to embed users and items into…

Transfer learning plays a key role in advancing machine learning models, yet conventional supervised pretraining often undermines feature transferability by prioritizing features that minimize the pretraining loss. In this work, we adapt a…

In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse effects on training from different samples, Selective Output…

Explanation regularisation (ER) has been introduced as a way to guide text classifiers to form their predictions relying on input tokens that humans consider plausible. This is achieved by introducing an auxiliary explanation loss that…

In active learning, the focus is mainly on the selection strategy of unlabeled data for enhancing the generalization capability of the next learning cycle. For this, various uncertainty measurement methods have been proposed. On the other…

The advent of large-scale pre-trained language models has contributed greatly to the recent progress in natural language processing. Many state-of-the-art language models are first trained on a large text corpus and then fine-tuned on…

Catastrophic forgetting(CF) is a significant challenge in continual learning (CL). In regularization-based approaches to mitigate CF, modifications to important training parameters are penalized in subsequent tasks using an appropriate loss…

Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…

Training a deep neural network with a small amount of data is a challenging problem as it is vulnerable to overfitting. However, one of the practical difficulties that we often face is to collect many samples. Transfer learning is a…