Related papers: Weakly supervised spoken term discovery using cros…
Audio-text retrieval enables semantic alignment between audio content and natural language queries, supporting applications in multimedia search, accessibility, and surveillance. However, current state-of-the-art approaches struggle with…
Our work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words. Recent works have focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and…
Domain Translation is the problem of finding a meaningful correspondence between two domains. Since in a majority of settings paired supervision is not available, much work focuses on Unsupervised Domain Translation (UDT) where data samples…
Developing Text Normalization (TN) systems for Text-to-Speech (TTS) on new languages is hard. We propose a novel architecture to facilitate it for multiple languages while using data less than 3% of the size of the data used by the state of…
Sound event detection (SED) is the task of identifying sound events along with their onset and offset times. A recent, convolutional neural networks based SED method, proposed the usage of depthwise separable (DWS) and time-dilated…
Language identification (LID) recognizes the language of a spoken utterance automatically. According to recent studies, LID models trained with an automatic speech recognition (ASR) task perform better than those trained with a LID task…
There has been growing interest in audio-language retrieval research, where the objective is to establish the correlation between audio and text modalities. However, most audio-text paired datasets often lack rich expression of the text…
As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the lexical semantics of words under specific contexts. Benefited from the large-scale annotation, current WSD…
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…
Neural networks are capable of translating between languages -- in some cases even between two languages where there is little or no access to parallel translations, in what is known as Unsupervised Machine Translation (UMT). Given this…
Retrieval-augmented generation can improve audio captioning by incorporating relevant audio-text pairs from a knowledge base. Existing methods typically rely solely on the input audio as a unimodal retrieval query. In contrast, we propose…
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through…
Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the…
Nonnegative Tucker decomposition (NTD), a tensor decomposition model, has received increased interest in the recent years because of its ability to blindly extract meaningful patterns, in particular in Music Information Retrieval.…
Discovering speaker independent acoustic units purely from spoken input is known to be a hard problem. In this work we propose an unsupervised speaker normalization technique prior to unit discovery. It is based on separating speaker…
Unsupervised discovery of acoustic tokens from audio corpora without annotation and learning vector representations for these tokens have been widely studied. Although these techniques have been shown successful in some applications such as…
Class imbalance naturally exists when train and test models in different domains. Unsupervised domain adaptation (UDA) augments model performance with only accessible annotations from the source domain and unlabeled data from the target…
Most of the speech translation models heavily rely on parallel data, which is hard to collect especially for low-resource languages. To tackle this issue, we propose to build a cascaded speech translation system without leveraging any kind…
The text generation paradigm for audio tasks has opened new possibilities for unified audio understanding. However, existing models face significant challenges in achieving a comprehensive understanding across diverse audio types, such as…
Prepositions are very common and very ambiguous, and understanding their sense is critical for understanding the meaning of the sentence. Supervised corpora for the preposition-sense disambiguation task are small, suggesting a…