Related papers: Focus on the present: a regularization method for …

In a world of proliferating data, the ability to rapidly summarize text is growing in importance. Automatic summarization of text can be thought of as a sequence to sequence problem. Another area of natural language processing that solves a…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduce the amount of labeled data needed for downstream task…

End-to-end speech-to-text translation typically suffers from the scarcity of paired speech-text data. One way to overcome this shortcoming is to utilize the bitext data from the Machine Translation (MT) task and perform Multi-Task Learning…

This work aims to predict channels in wireless communication systems based on noisy observations, utilizing sequence-to-sequence models with attention (Seq2Seq-attn) and transformer models. Both models are adapted from natural language…

Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge, particularly for dense prediction. In this paper we…

Recent advances in Automatic Speech Recognition (ASR) demonstrated how end-to-end systems are able to achieve state-of-the-art performance. There is a trend towards deeper neural networks, however those ASR models are also more complex and…

Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source languages or modalities. We propose two novel approaches to…

In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstraction gap between input acoustic signals and output linguistic…

Modern speech processing systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down inference and training and increasing memory consumption.…

Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to…

End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse…

Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repeat words or produce…

Siamese networks have shown effective results in unsupervised visual representation learning. These models are designed to learn an invariant representation of two augmentations for one input by maximizing their similarity. In this paper,…

In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that…

Connectionist Temporal Classification has recently attracted a lot of interest as it offers an elegant approach to building acoustic models (AMs) for speech recognition. The CTC loss function maps an input sequence of observable feature…

Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However,…

Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from…

Multi-talker speech recognition (MTASR) faces unique challenges in disentangling and transcribing overlapping speech. To address these challenges, this paper investigates the role of Connectionist Temporal Classification (CTC) in speaker…

Despite recent advances in end-to-end speech recognition methods, the output tends to be biased to the training data's vocabulary, resulting in inaccurate recognition of proper nouns and other unknown terms. To address this issue, we…