Related papers: Unsupervised Word Segmentation from Speech with At…

Past work on unsupervised parsing is constrained to written form. In this paper, we present the first study on unsupervised spoken constituency parsing given unlabeled spoken sentences and unpaired textual data. The goal is to determine the…

This paper proposes a new demand estimation method using attention-based language models. An encoder-only language model is trained in a two-stage process to analyze the natural language descriptions of used cars from a large US-based…

We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…

Language models provide a key framework for studying linguistic theories based on prediction, but phonological analysis using large language models (LLMs) is difficult; there are few phonological benchmarks beyond English and the standard…

Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning methods require large amounts of labeled data for training. Manual annotation is expensive, while simulators can…

Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with…

This paper introduces a method for image semantic segmentation grounded on a novel fusion scheme, which takes place inside a deep convolutional neural network. The main goal of our proposal is to explore object boundary information to…

This work presents a broad study on the adaptation of neural network acoustic models by means of learning hidden unit contributions (LHUC) -- a method that linearly re-combines hidden units in a speaker- or environment-dependent manner…

We present the Zero Resource Speech Challenge 2020, which aims at learning speech representations from raw audio signals without any labels. It combines the data sets and metrics from two previous benchmarks (2017 and 2019) and features two…

Active learning for sentence understanding aims at discovering informative unlabeled data for annotation and therefore reducing the demand for labeled data. We argue that the typical uncertainty sampling method for active learning is…

Speech intelligibility can be affected by multiple factors, such as noisy environments, channel distortions or physiological issues. In this work, we deal with the problem of automatic prediction of the speech intelligibility level in this…

Certain spans of utterances in a discourse, referred to here as segments, are widely assumed to form coherent units. Further, the segmental structure of discourse has been claimed to constrain and be constrained by many phenomena. However,…

Speech recognition has become an important task in the development of machine learning and artificial intelligence. In this study, we explore the important task of keyword spotting using speech recognition machine learning and deep learning…

Chinese word segmentation has entered the deep learning era which greatly reduces the hassle of feature engineering. Recently, some researchers attempted to treat it as character-level translation, which further simplified model designing,…

Segmentation of handwritten document images into text lines and words is one of the most significant and challenging tasks in the development of a complete Optical Character Recognition (OCR) system. This paper addresses the automatic…

Machine unlearning, the process of efficiently removing specific information from machine learning models, is a growing area of interest for responsible AI. However, few studies have explored the effectiveness of unlearning methods on…

In this paper, we propose a novel architecture for direct extractive speech-to-speech summarization, ESSumm, which is an unsupervised model without dependence on intermediate transcribed text. Different from previous methods with text…

We present a probabilistic model that uses both prosodic and lexical cues for the automatic segmentation of speech into topically coherent units. We propose two methods for combining lexical and prosodic information using hidden Markov…

In this work, we explore a multimodal semi-supervised learning approach for punctuation prediction by learning representations from large amounts of unlabelled audio and text data. Conventional approaches in speech processing typically use…

User interaction with voice-powered agents generates large amounts of unlabeled utterances. In this paper, we explore techniques to efficiently transfer the knowledge from these unlabeled utterances to improve model performance on Spoken…