Related papers: Confusion2Vec: Towards Enriching Vector Space Word…

Skip-gram (word2vec) is a recent method for creating vector representations of words ("distributed word representations") using a neural network. The representation gained popularity in various areas of natural language processing, because…

Despite recent advancements in deep learning technologies, Child Speech Recognition remains a challenging task. Current Automatic Speech Recognition (ASR) models require substantial amounts of annotated data for training, which is scarce.…

Audio-visual speech recognition (AVSR) combines audio-visual modalities to improve speech recognition, especially in noisy environments. However, most existing methods deploy the unidirectional enhancement or symmetric fusion manner, which…

Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation datasets. We show…

Word vector representations are well developed tools for various NLP and Machine Learning tasks and are known to retain significant semantic and syntactic structure of languages. But they are prone to carrying and amplifying bias which can…

Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply…

Generating spoken word embeddings that possess semantic information is a fascinating topic. Compared with text-based embeddings, they cover both phonetic and semantic characteristics, which can provide richer information and are potentially…

Approaching Speech-to-Text and Automatic Speech Recognition problems in low-resource languages is notoriously challenging due to the scarcity of validated datasets and the diversity of dialects. Arabic, Russian, and Portuguese exemplify…

Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate…

Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech)…

In recent years, word embeddings have been surprisingly effective at capturing intuitive characteristics of the words they represent. These vectors achieve the best results when training corpora are extremely large, sometimes billions of…

Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and…

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…

Dimensional representations of speech emotions such as the arousal-valence (AV) representation provide a continuous and fine-grained description and control than their categorical counterparts. They have wide applications in tasks such as…

Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR). However, the robustness impact of combining the two…

Distributional representations of words, also known as word vectors, have become crucial for modern natural language processing tasks due to their wide applications. Recently, a growing body of word vector postprocessing algorithm has…

Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…

Text classification has become indispensable due to the rapid increase of text in digital form. Over the past three decades, efforts have been made to approach this task using various learning algorithms and statistical models based on…

Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…

Evaluating L2 speech intelligibility is crucial for effective computer-assisted language learning (CALL). Conventional ASR-based methods often focus on native-likeness, which may fail to capture the actual intelligibility perceived by human…