Related papers: Leveraging multilingual transfer for unsupervised …

We present a novel method for extracting neural embeddings that model the background acoustics of a speech signal. The extracted embeddings are used to estimate specific parameters related to the background acoustic properties of the signal…

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

This paper presents an accurate phoneme alignment model that aims for speech analysis and video content creation. We propose a variational autoencoder (VAE)-based alignment model in which a probable path is searched using encoded acoustic…

Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…

Large-scale auto-regressive language models pretrained on massive text have demonstrated their impressive ability to perform new natural language tasks with only a few text examples, without the need for fine-tuning. Recent studies further…

The goal of sexism detection is to mitigate negative online content targeting certain gender groups of people. However, the limited availability of labeled sexism-related datasets makes it problematic to identify online sexism for…

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

We study the usability of pre-trained weakly supervised audio tagging (AT) models as feature extractors for general audio representations. We mainly analyze the feasibility of transferring those embeddings to other tasks within the speech…

To be able to interact better with humans, it is crucial for machines to understand sound - a primary modality of human perception. Previous works have used sound to learn embeddings for improved generic textual similarity assessment. In…

Sentiment analysis in low-resource languages suffers from a lack of annotated corpora to estimate high-performing models. Machine translation and bilingual word embeddings provide some relief through cross-lingual sentiment approaches.…

In this paper, we develop a novel approach to aspect term extraction based on unsupervised learning of distributed representations of words and dependency paths. The basic idea is to connect two words (w1 and w2) with the dependency path…

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Target sound extraction consists of extracting the sound of a target acoustic event (AE) class from a mixture of AE sounds. It can be realized using a neural network that extracts the target sound conditioned on a 1-hot vector that…

Machine comprehension(MC) style question answering is a representative problem in natural language processing. Previous methods rarely spend time on the improvement of encoding layer, especially the embedding of syntactic information and…

Sense embedding learning methods learn multiple vectors for a given ambiguous word, corresponding to its different word senses. For this purpose, different methods have been proposed in prior work on sense embedding learning that use…

Traditional transformer-based semantic segmentation relies on quantized embeddings. However, our analysis reveals that autoencoder accuracy on segmentation mask using quantized embeddings (e.g. VQ-VAE) is 8% lower than continuous-valued…

With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural language models used today. However, as only a single…

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…