Related papers: Stutter-Solver: End-to-end Multi-lingual Dysfluenc…
In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed. This post-processing step is crucial for producing clean transcripts and high performance on downstream tasks…
This study explores a comprehensive approach to obstacle detection using advanced YOLO models, specifically YOLOv8, YOLOv7, YOLOv6, and YOLOv5. Leveraging deep learning techniques, the research focuses on the performance comparison of these…
Speech is a hierarchical collection of text, prosody, emotions, dysfluencies, etc. Automatic transcription of speech that goes beyond text (words) is an underexplored problem. We focus on transcribing speech along with non-fluencies…
Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text. Moreover, most works focus on leveraging only contextual information captured by the linear…
Self-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing and disfluency detection in speech transcripts. Since the contextualized word…
Video text spotting (VTS) aims to simultaneously localize, recognize and track text instances in videos. To address the limited recognition capability of end-to-end methods, recent methods track the zero-shot results of state-of-the-art…
Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on visual cues and implicitly capture local character…
End-to-end approaches open a new way for more accurate and efficient spoken language understanding (SLU) systems by alleviating the drawbacks of traditional pipeline systems. Previous works exploit textual information for an SLU model via…
Most existing speech disfluency detection techniques only rely upon acoustic data. In this work, we present a practical multimodal disfluency detection approach that leverages available video data together with audio. We curate an…
Stuttering, also called stammering, is a communication disorder that breaks the continuity of the speech. This program of work is an attempt to develop automatic recognition procedures to assess stuttered dysfluencies and use these…
Text detection and recognition in natural images have long been considered as two separate tasks that are processed sequentially. Training of two tasks in a unified framework is non-trivial due to significant dif- ferences in optimisation…
This paper studies the performance of a neural self-attentive parser on transcribed speech. Speech presents parsing challenges that do not appear in written text, such as the lack of punctuation and the presence of speech disfluencies…
Text spotting end-to-end methods have recently gained attention in the literature due to the benefits of jointly optimizing the text detection and recognition components. Existing methods usually have a distinct separation between the…
Most existing approaches to disfluency detection heavily rely on human-annotated corpora, which is expensive to obtain in practice. There have been several proposals to alleviate this issue with, for instance, self-supervised learning…
End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although…
Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they are evaluated only on high-resource languages. We…
Streaming end-to-end multi-talker speech recognition aims at transcribing the overlapped speech from conversations or meetings with an all-neural model in a streaming fashion, which is fundamentally different from a modular-based approach…
Despite decades of advancements, the simulation of fluids remains one of the most challenging areas of in scientific computing. Supported by the necessity of gradient information in deep learning, differentiable simulators have emerged as…
Complete blood cell detection holds significant value in clinical diagnostics. Conventional manual microscopy methods suffer from time inefficiency and diagnostic inaccuracies. Existing automated detection approaches remain constrained by…
Dyslexia affects reading and writing skills across many languages. This work describes a new application of YOLO-based object detection to isolate and label handwriting patterns (Normal, Reversal, Corrected) within synthetic images that…