Related papers: Masked Self-distilled Transducer-based Keyword Spo…

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

Designing an efficient keyword spotting (KWS) system that delivers exceptional performance on resource-constrained edge devices has long been a subject of significant attention. Existing KWS search algorithms typically follow a…

The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR). To estimate the output distributions over subword units, RNN-T uses a fully connected…

Non-autoregressive (NAR) neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model. Under this framework, we leverage large monolingual corpora to improve the NAR model's performance, with the…

Recently, attention-based encoder-decoder (AED) end-to-end (E2E) models have drawn more and more attention in the field of automatic speech recognition (ASR). AED models, however, still have drawbacks when deploying in commercial…

Non-autoregressive (NAR) models generate all the tokens of a sequence in parallel, resulting in faster generation speed compared to their autoregressive (AR) counterparts but at the cost of lower accuracy. Different techniques including…

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…

Vision Transformers (ViTs) emerge to achieve impressive performance on many data-abundant computer vision tasks by capturing long-range dependencies among local features. However, under few-shot learning (FSL) settings on small datasets…

Non-Autoregressive generation is a sequence generation paradigm, which removes the dependency between target tokens. It could efficiently reduce the text generation latency with parallel decoding in place of token-by-token sequential…

Supervised fine-tuning methods (SFT) perform great efficiency on artificial intelligence interpretation in SAR images, leveraging the powerful representation knowledge from pre-training models. Due to the lack of domain-specific pre-trained…

In this work, we propose a novel and efficient minimum word error rate (MWER) training method for RNN-Transducer (RNN-T). Unlike previous work on this topic, which performs on-the-fly limited-size beam-search decoding and generates…

Supervised multi-view stereo (MVS) methods have achieved remarkable progress in terms of reconstruction quality, but suffer from the challenge of collecting large-scale ground-truth depth. In this paper, we propose a novel self-supervised…

Knowledge distillation (KD) methods compress large models into smaller students with manually-designed student architectures given pre-specified computational cost. This requires several trials to find a viable student, and further…

In this paper, we present a novel approach to adapt a sequence-to-sequence Transformer-Transducer ASR system to the keyword spotting (KWS) task. We achieve this by replacing the keyword in the text transcription with a special token <kw>…

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

In text classification tasks, fine tuning pretrained language models like BERT and GPT-3 yields competitive accuracy; however, both methods require pretraining on large text datasets. In contrast, general topic modeling methods possess the…

This paper presents the use of non-autoregressive (NAR) approaches for joint automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. The proposed NAR systems employ a Conformer encoder that applies connectionist…

Knowledge distillation (KD) is essential for training non-autoregressive translation (NAT) models by reducing the complexity of the raw data with an autoregressive teacher model. In this study, we empirically show that as a side effect of…

The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain.…

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small models. In this study, we…