Related papers: SegINR: Segment-wise Implicit Neural Representatio…

In current clinical practices, electroencephalograms (EEG) are reviewed and analyzed by trained neurologists to provide supports for therapeutic decisions. Manual reviews can be laborious and error prone. Automatic and accurate…

With the rapid evolution of autonomous driving technology and intelligent transportation systems, semantic segmentation has become increasingly critical. Precise interpretation and analysis of real-world environments are indispensable for…

Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…

Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual…

Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally…

We combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing. Character representations can easily be added in a sequence-to-sequence model in either one…

A major obstacle to building models for effective semantic segmentation, and particularly video semantic segmentation, is a lack of large and well annotated datasets. This bottleneck is particularly prohibitive in highly specialized and…

We propose a new continuous video modeling framework based on implicit neural representations (INRs) called ActINR. At the core of our approach is the observation that INRs can be considered as a learnable dictionary, with the shapes of the…

We present Generative Semantic Segmentation (GSS), a generative learning approach for semantic segmentation. Uniquely, we cast semantic segmentation as an image-conditioned mask generation problem. This is achieved by replacing the…

This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are…

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

Scene text recognition has attracted a great many researches due to its importance to various applications. Existing methods mainly adopt recurrence or convolution based networks. Though have obtained good performance, these methods still…

Sequence to Sequence models, in particular the Transformer, achieve state of the art results in Automatic Speech Recognition. Practical usage is however limited to cases where full utterance latency is acceptable. In this work we introduce…

Recent zero-shot text-to-speech (TTS) systems face a common dilemma: autoregressive (AR) models suffer from slow generation and lack duration controllability, while non-autoregressive (NAR) models lack temporal modeling and typically…

In this work, we investigate the use of spatio-temporalImplicit Neural Representations (INRs) for dynamic X-ray computed tomography (XCT) reconstruction under interlaced acquisition schemes. The proposed approach combines ADMM-based…

Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a…

Speech Emotion Recognition (SER) is widely deployed in Human-Computer Interaction, yet the high computational cost of conventional models hinders their implementation on resource-constrained edge devices. Spiking Neural Networks (SNNs)…

Many autonomous robotic applications require object-level understanding when deployed. Actively reconstructing objects of interest, i.e. objects with specific semantic meanings, is therefore relevant for a robot to perform downstream tasks…

Implicit neural representations (INRs) such as NeRF and SIREN encode a signal in neural network parameters and show excellent results for signal reconstruction. Using INRs for downstream tasks, such as classification, is however not…

Confidence estimation of predictions from an End-to-End (E2E) Automatic Speech Recognition (ASR) model benefits ASR's downstream and upstream tasks. Class-probability-based confidence scores do not accurately represent the quality of…