Related papers: FSR: Accelerating the Inference Process of Transdu…

Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and generally suffer from low inference speed, which limits their…

Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do…

Visual Speech Recognition (VSR) aims to infer speech into text depending on lip movements alone. As it focuses on visual information to model the speech, its performance is inherently sensitive to personal lip appearances and movements, and…

There is often a trade-off between performance and latency in streaming automatic speech recognition (ASR). Traditional methods such as look-ahead and chunk-based methods, usually require information from future frames to advance…

Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…

Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient training and inference, we carefully redesigned Conformer with a…

Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational…

Deep sequence recognition (DSR) models receive increasing attention due to their superior application to various applications. Most DSR models use merely the target sequences as supervision without considering other related sequences,…

Tucker decomposition is one of the SOTA CNN model compression techniques. However, unlike the FLOPs reduction, we observe very limited inference time reduction with Tucker-compressed models using existing GPU software such as cuDNN. To this…

Learned Sparse Retrieval (LSR) is an effective IR approach that exploits pre-trained language models for encoding text into a learned bag of words. Several efforts in the literature have shown that sparsity is key to enabling a good…

This thesis addresses automatic lexical error recovery and tokenization of corrupt text input. We propose a technique that can automatically correct misspellings, segmentation errors and real-word errors in a unified framework that uses…

Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to…

In this paper, a time delay neural network (TDNN) based acoustic model is proposed to implement a fast-converged acoustic modeling for Korean speech recognition. The TDNN has an advantage in fast-convergence where the amount of training…

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…

Speech separation is an important problem in speech processing, which targets to separate and generate clean speech from a mixed audio containing speech from different speakers. Empowered by the deep learning technologies over…

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…

End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…

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…

The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. During training, the memory requirements may quickly exceed the…

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. Conventionally trained using the task-specific objective, i.e., cross-entropy loss, prompts tend to…