Related papers: Multilingual acoustic word embeddings for zero-res…
Cross-lingual Speech Emotion Recognition (CLSER) aims to identify emotional states in unseen languages. However, existing methods heavily rely on the semantic synchrony of complete labels and static feature stability, hindering low-resource…
Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…
We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit…
Speaker identification in multilingual settings presents unique challenges, particularly when conventional models are predominantly trained on English data. In this paper, we propose WSI (Whisper Speaker Identification), a framework that…
Despite advancements in speech recognition, accented speech remains challenging. While previous approaches have focused on modeling techniques or creating accented speech datasets, gathering sufficient data for the multitude of accents,…
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…
The performance of many network learning applications crucially hinges on the success of network embedding algorithms, which aim to encode rich network information into low-dimensional vertex-based vector representations. This paper…
In zero-resource settings where transcribed speech audio is unavailable, unsupervised feature learning is essential for downstream speech processing tasks. Here we compare two recent methods for frame-level acoustic feature learning. For…
With a surge in the usage of social media postings to express opinions, emotions, and ideologies, there has been a significant shift towards the calibration of social media as a rapid medium of conveying viewpoints and outlooks over the…
Speech recognition in noisy and channel distorted scenarios is often challenging as the current acoustic modeling schemes are not adaptive to the changes in the signal distribution in the presence of noise. In this work, we develop a novel…
Building automatic speech recognition (ASR) systems is a challenging task, especially for under-resourced languages that need to construct corpora nearly from scratch and lack sufficient training data. It has emerged that several African…
Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…
Several language applications often require word semantics as a core part of their processing pipeline, either as precise meaning inference or semantic similarity. Multi-sense embeddings (M-SE) can be exploited for this important…
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the…
We propose a new method of generating meaningful embeddings for speech, changes to four commonly used meta learning approaches to enable them to perform keyword spotting in continuous signals and an approach of combining their outcomes into…
Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…
Contextualized word embeddings (CWE) such as provided by ELMo (Peters et al., 2018), Flair NLP (Akbik et al., 2018), or BERT (Devlin et al., 2019) are a major recent innovation in NLP. CWEs provide semantic vector representations of words…
The pervasiveness of the Internet and social media have enabled the rapid and anonymous spread of Hate Speech content on microblogging platforms such as Twitter. Current EU and US legislation against hateful language, in conjunction with…
We study the selection of transfer languages for automatic abusive language detection. Instead of preparing a dataset for every language, we demonstrate the effectiveness of cross-lingual transfer learning for zero-shot abusive language…
In this paper, we propose a novel end-to-end user-defined keyword spotting method that utilizes linguistically corresponding patterns between speech and text sequences. Unlike previous approaches requiring speech keyword enrollment, our…