Related papers: Fine-grained Language Identification with Multilin…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Multi-lingual speech recognition aims to distinguish linguistic expressions in different languages and integrate acoustic processing simultaneously. In contrast, current multi-lingual speech recognition research follows a language-aware…

Long-context understanding poses significant challenges in natural language processing, particularly for real-world dialogues characterized by speech-based elements, high redundancy, and uneven information density. Although large language…

Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be…

Advances in Natural Language Processing (NLP) have revolutionized the way researchers and practitioners address crucial societal problems. Large language models are now the standard to develop state-of-the-art solutions for text detection…

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios, data labels are…

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…

Fine-tuning pretrained language models (LMs) without making any architectural changes has become a norm for learning various language downstream tasks. However, for non-language downstream tasks, a common practice is to employ task-specific…

This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseN-ets are very deep, compact convolutional neural networks, which have…

The recent advances in deep learning are mostly driven by availability of large amount of training data. However, availability of such data is not always possible for specific tasks such as speaker recognition where collection of large…

Open-vocabulary detectors are proposed to locate and recognize objects in novel classes. However, variations in vision-aware language vocabulary data used for open-vocabulary learning can lead to unfair and unreliable evaluations. Recent…

This work investigates the use of large-scale, English-only pre-trained models (CLIP and HuBERT) for multilingual image-speech retrieval. For non-English image-speech retrieval, we outperform the current state-of-the-art performance by a…

Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no supervision, but they…

Nowadays, most methods in end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance…

The goal of this work is to automatically determine whether and when a word of interest is spoken by a talking face, with or without the audio. We propose a zero-shot method suitable for in the wild videos. Our key contributions are: (1) a…

In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose…

Lensless cameras are characterized by several advantages (e.g., miniaturization, ease of manufacture, and low cost) as compared with conventional cameras. However, they have not been extensively employed due to their poor image clarity and…

Audio-visual speech separation aims to isolate each speaker's clean voice from mixtures by leveraging visual cues such as lip movements and facial features. While visual information provides complementary semantic guidance, existing methods…

Visual speech recognition is a technique to identify spoken content in silent speech videos, which has raised significant attention in recent years. Advancements in data-driven deep learning methods have significantly improved both the…

A large number of pornographic audios publicly available on the Internet seriously threaten the mental and physical health of children, but these audios are rarely detected and filtered. In this paper, we firstly propose a convolutional…