相关论文: Audio-Visual Neural Syntax Acquisition

Audio-visual speech enhancement (AVSE) methods use both audio and visual features for the task of speech enhancement and the use of visual features has been shown to be particularly effective in multi-speaker scenarios. In the majority of…

Video-to-speech synthesis involves reconstructing the speech signal of a speaker from a silent video. The implicit assumption of this task is that the sound signal is either missing or contains a high amount of noise/corruption such that it…

Audio-Visual Speech Recognition (AVSR) models have surpassed their audio-only counterparts in terms of performance. However, the interpretability of AVSR systems, particularly the role of the visual modality, remains under-explored. In this…

We present DenseAV, a novel dual encoder grounding architecture that learns high-resolution, semantically meaningful, and audio-visually aligned features solely through watching videos. We show that DenseAV can discover the ``meaning'' of…

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of…

This paper addresses a fundamental problem of scene understanding: How to parse the scene image into a structured configuration (i.e., a semantic object hierarchy with object interaction relations) that finely accords with human perception.…

The objective of Audio-Visual Segmentation (AVS) is to localise the sounding objects within visual scenes by accurately predicting pixel-wise segmentation masks. To tackle the task, it involves a comprehensive consideration of both the data…

Much recent work on Spoken Language Understanding (SLU) falls short in at least one of three ways: models were trained on oracle text input and neglected the Automatics Speech Recognition (ASR) outputs, models were trained to predict only…

We propose a segmental neural language model that combines the generalization power of neural networks with the ability to discover word-like units that are latent in unsegmented character sequences. In contrast to previous segmentation…

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…

Lip reading is used to understand or interpret speech without hearing it, a technique especially mastered by people with hearing difficulties. The ability to lip read enables a person with a hearing impairment to communicate with others and…

Both acoustic and visual information influence human perception of speech. For this reason, the lack of audio in a video sequence determines an extremely low speech intelligibility for untrained lip readers. In this paper, we present a way…

Infants gradually learn to parse continuous speech into words and connect names with objects, yet the mechanisms behind development of early word perception skills remain unknown. We studied the extent to which early words can be acquired…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast,…

Generating structured query language (SQL) from natural language is an emerging research topic. This paper presents a new learning paradigm from indirect supervision of the answers to natural language questions, instead of SQL queries. This…

Vision-language (VL) pre-training has recently gained much attention for its transferability and flexibility in novel concepts (e.g., cross-modality transfer) across various visual tasks. However, VL-driven segmentation has been…

Visually-grounded models of spoken language understanding extract semantic information directly from speech, without relying on transcriptions. This is useful for low-resource languages, where transcriptions can be expensive or impossible…

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…