Related papers: E2E Segmentation in a Two-Pass Cascaded Encoder AS…

Decoding continuous speech from intracortical recordings is a central challenge for brain-computer interfaces (BCIs), with transformative potential for individuals with conditions that impair their ability to speak. While recent…

In end-to-end (E2E) speech recognition models, a representational tight-coupling inevitably emerges between the encoder and the decoder. We build upon recent work that has begun to explore building encoders with modular encoded…

This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS).…

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

Classic embedded feature selection algorithms are often divided in two large groups: tree-based algorithms and lasso variants. Both approaches are focused in different aspects: while the tree-based algorithms provide a clear explanation…

Neural networks have proven to be a formidable tool to tackle the problem of speech coding at very low bit rates. However, the design of a neural coder that can be operated robustly under real-world conditions remains a major challenge.…

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages,…

Video Object Segmentation (VOS) is typically formulated in a semi-supervised setting. Given the ground-truth segmentation mask on the first frame, the task of VOS is to track and segment the single or multiple objects of interests in the…

Conventional automatic speech recognition (ASR) models typically produce outputs as normalized texts lacking punctuation and capitalization, necessitating post-processing models to enhance readability. This approach, however, introduces…

A new deep learning-based electroencephalography (EEG) signal analysis framework is proposed. While deep neural networks, specifically convolutional neural networks (CNNs), have gained remarkable attention recently, they still suffer from…

There has been an increased interest in the integration of pretrained speech recognition (ASR) and language models (LM) into the SLU framework. However, prior methods often struggle with a vocabulary mismatch between pretrained models, and…

In streaming automatic speech recognition (ASR), it is desirable to reduce latency as much as possible while having minimum impact on recognition accuracy. Although a few existing methods are able to achieve this goal, they are difficult to…

Recently, the unified streaming and non-streaming two-pass (U2/U2++) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy and latency. In this paper, we present fast-U2++, an…

We study the problem of improving the efficiency of segmentation transformers by using disparate amounts of computation for different parts of the image. Our method, PAUMER, accomplishes this by pausing computation for patches that are…

Speech Emotion Recognition (SER) often operates on speech segments detected by a Voice Activity Detection (VAD) model. However, VAD models may output flawed speech segments, especially in noisy environments, resulting in degraded…

This paper develops a novel encoder-decoder deep network architecture which exploits the several contextual frames of 2D+t sequential images in a sliding window centered at current frame to segment 2D vessel masks from the current frame.…

Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle…

Variational auto-encoder (VAE) is a powerful unsupervised learning framework for image generation. One drawback of VAE is that it generates blurry images due to its Gaussianity assumption and thus L2 loss. To allow the generation of high…

The primary paradigm in Neural Combinatorial Optimization (NCO) are construction methods, where a neural network is trained to sequentially add one solution component at a time until a complete solution is constructed. We observe that the…

Among various sensors for assisted and autonomous driving systems, automotive radar has been considered as a robust and low-cost solution even in adverse weather or lighting conditions. With the recent development of radar technologies and…