Related papers: Word Segmentation on Discovered Phone Units with D…
Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…
Deep neural network (DNN) based end-to-end optimization in the complex time-frequency (T-F) domain or time domain has shown considerable potential in monaural speech separation. Many recent studies optimize loss functions defined solely in…
This paper considers the impact of automatic segmentation on the fully-automatic, semi-supervised training of automatic speech recognition (ASR) systems for five-lingual code-switched (CS) speech. Four automatic segmentation techniques were…
This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…
In this work, we present Lexical Unit Analysis (LUA), a framework for general sequence segmentation tasks. Given a natural language sentence, LUA scores all the valid segmentation candidates and utilizes dynamic programming (DP) to extract…
Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training. To address the above problem, we consider an efficient…
Mispronunciation detection and diagnosis (MDD) is a significant part in modern computer-aided language learning (CALL) systems. Most systems implementing phoneme-level MDD through goodness of pronunciation (GOP), however, rely on…
While promptable segmentation (\textit{e.g.}, SAM) has shown promise for various segmentation tasks, it still requires manual visual prompts for each object to be segmented. In contrast, task-generic promptable segmentation aims to reduce…
Tokenizing raw texts into word units is an essential pre-processing step for critical tasks in the NLP pipeline such as tagging, parsing, named entity recognition, and more. For most languages, this tokenization step straightforward.…
Temporal spike recognition plays a crucial role in various domains, including anomaly detection, keyword spotting and neuroscience. This paper presents a novel algorithm for efficient temporal spike pattern recognition on sparse event…
Neural word representations have proven useful in Natural Language Processing (NLP) tasks due to their ability to efficiently model complex semantic and syntactic word relationships. However, most techniques model only one representation…
Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses…
The task of estimating the maximum number of concurrent speakers from single channel mixtures is important for various audio-based applications, such as blind source separation, speaker diarisation, audio surveillance or auditory scene…
Deep clustering is a recently introduced deep learning architecture that uses discriminatively trained embeddings as the basis for clustering. It was recently applied to spectrogram segmentation, resulting in impressive results on…
Discourse segmentation aims to segment Elementary Discourse Units (EDUs) and is a fundamental task in discourse analysis. For Chinese, previous researches identify EDUs just through discriminating the functions of punctuations. In this…
Audio commands are a preferred communication medium to keep inspectors in the loop of civil infrastructure inspection performed by a semi-autonomous drone. To understand job-specific commands from a group of heterogeneous and dynamic…
Self-supervised representation learning for speech often involves a quantization step that transforms the acoustic input into discrete units. However, it remains unclear how to characterize the relationship between these discrete units and…
Open vocabulary object detection has been greatly advanced by the recent development of vision-language pretrained model, which helps recognize novel objects with only semantic categories. The prior works mainly focus on knowledge…
Using audio and text embeddings jointly for Keyword Spotting (KWS) has shown high-quality results, but the key challenge of how to semantically align two embeddings for multi-word keywords of different sequence lengths remains largely…
Although deep learning has substantially advanced speech separation in recent years, most existing studies continue to prioritize separation quality while overlooking computational efficiency, an essential factor for low-latency speech…