相关论文: A Glance is Enough: Extract Target Sentence By Loo…

We propose a novel framework for target speech extraction based on semantic information, called ConceptBeam. Target speech extraction means extracting the speech of a target speaker in a mixture. Typical approaches have been exploiting…

Past work in computational sarcasm deals primarily with sarcasm detection. In this paper, we introduce a novel, related problem: sarcasm target identification i.e., extracting the target of ridicule in a sarcastic sentence). We present an…

We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded…

Speaker extraction seeks to extract the target speech in a multi-talker scenario given an auxiliary reference. Such reference can be auditory, i.e., a pre-recorded speech, visual, i.e., lip movements, or contextual, i.e., phonetic sequence.…

Sentence simplification aims to improve readability and understandability, based on several operations such as splitting, deletion, and paraphrasing. However, a valid simplified sentence should also be logically entailed by its input…

A sentence can be translated into more than one correct sentences. However, most of the existing neural machine translation models only use one of the correct translations as the targets, and the other correct sentences are punished as the…

This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR…

We propose a model of the speech perception of individual words in the presence of mishearings. This phenomenological approach is based on concepts used in linguistics, and provides a formalism that is universal across languages. We put…

English proficiency assessments have become a necessary metric for filtering and selecting prospective candidates for both academia and industry. With the rise in demand for such assessments, it has become increasingly necessary to have the…

An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents. We focus on improving performance of end-to-end Automatic…

The multi-head self-attention of popular transformer models is widely used within Natural Language Processing (NLP), including for the task of extractive summarization. With the goal of analyzing and pruning the parameter-heavy…

Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing…

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We…

When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the…

We consider retrofitting structure-aware Transformer-based language model for facilitating end tasks by proposing to exploit syntactic distance to encode both the phrasal constituency and dependency connection into the language model. A…

Text simplification aims at making a text easier to read and understand by simplifying grammar and structure while keeping the underlying information identical. It is often considered an all-purpose generic task where the same…

Target speech extraction is a technique to extract the target speaker's voice from mixture signals using a pre-recorded enrollment utterance that characterize the voice characteristics of the target speaker. One major difficulty of target…