Related papers: Subword Regularization: An Analysis of Scalability…

We present an unsupervised word segmentation model, in which the learning objective is to maximize the generation probability of a sentence given its all possible segmentation. Such generation probability can be factorized into the…

In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair encoding (BPE) and its variants are the predominant approach…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

Subword segmenters like BPE operate as a preprocessing step in neural machine translation and other (conditional) language models. They are applied to datasets before training, so translation or text generation quality relies on the quality…

Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples. In addition to weight decay,…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM) approach that…

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…

Overfitting is one of the most critical challenges in deep neural networks, and there are various types of regularization methods to improve generalization performance. Injecting noises to hidden units during training, e.g., dropout, is…

We propose a new method of generating meaningful embeddings for speech, changes to four commonly used meta learning approaches to enable them to perform keyword spotting in continuous signals and an approach of combining their outcomes into…

Word embeddings have been shown to benefit from ensambling several word embedding sources, often carried out using straightforward mathematical operations over the set of word vectors. More recently, self-supervised learning has been used…

This paper introduces Dynamic Programming Encoding (DPE), a new segmentation algorithm for tokenizing sentences into subword units. We view the subword segmentation of output sentences as a latent variable that should be marginalized out…

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped…

Predicting the altered acoustic frames is an effective way of self-supervised learning for speech representation. However, it is challenging to prevent the pretrained model from overfitting. In this paper, we proposed to introduce two…

Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and…

Speech summarization is typically performed by using a cascade of speech recognition and text summarization models. End-to-end modeling of speech summarization models is challenging due to memory and compute constraints arising from long…

Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…

Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in…