相关论文: The Statistical Model for Ticker, an Adaptive Sing…

Overlapping speech remains a major challenge for automatic speech recognition (ASR) in real-world applications, particularly in broadcast media with dynamic, multi-speaker interactions. We propose a light-weight, target-speaker-based…

Image captioning creates informative text from an input image by creating a relationship between the words and the actual content of an image. Recently, deep learning models that utilize transformers have been the most successful in…

Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advances, ASR models like Whisper struggle with non-normative…

Stopword removal is a critical stage in many Machine Learning methods but often receives little consideration, it interferes with the model visualizations and disrupts user confidence. Inappropriately chosen or hastily omitted stopwords not…

Differing from the conventional communication system paradigm that models information source as a sequence of (i.i.d. or stationary) random variables, the semantic approach aims at extracting and sending the high-level features of the…

Resources such as bandwidth and energy are limited in many wireless communications use cases, especially when large numbers of sensors and fusion centers need to exchange information frequently. One opportunity to overcome resource…

There is amazing progress in Deep Learning based models for Image captioning and Low Light image enhancement. For the first time in literature, this paper develops a Deep Learning model that translates night scenes to sentences, opening new…

The problem of recovering graph signals is one of the main topics in graph signal processing. A representative approach to this problem is the graph Wiener filter, which utilizes the statistical information of the target signal computed…

Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Recommender systems often use text-side information to improve their predictions, especially in cold-start or zero-shot recommendation scenarios, where traditional collaborative filtering approaches cannot be used. Many approaches to…

Accurate recognition of rare and new words remains a pressing problem for contextualized Automatic Speech Recognition (ASR) systems. Most context-biasing methods involve modification of the ASR model or the beam-search decoding algorithm,…

Speaker recognition is a well known and studied task in the speech processing domain. It has many applications, either for security or speaker adaptation of personal devices. In this paper, we present a new paradigm for automatic speaker…

Transformer becomes more popular in the vision domain in recent years so there is a need for finding an effective way to interpret the Transformer model by visualizing it. In recent work, Chefer et al. can visualize the Transformer on…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Understanding how attention varies across individuals has significant scientific and societal impacts. However, existing visual scanpath models treat attention uniformly, neglecting individual differences. To bridge this gap, this paper…

We address the problem of cross-speaker style transfer for text-to-speech (TTS) using data augmentation via voice conversion. We assume to have a corpus of neutral non-expressive data from a target speaker and supporting conversational…

Standard decoding strategies for text generation, including top-k, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting selection to high-probability regions. Human language production operates…

The people in the world who are hearing impaired face many obstacles in communication and require an interpreter to comprehend what a person is saying. There has been constant scientific research and the existing models lack the ability to…

Interaction is a fundamental part of using any computer system but it is still an issue for people with special needs. In order to improve this situation, this paper describes a new device-interaction model based on adaptation rules for…