Related papers: SLiCK: Exploiting Subsequences for Length-Constrai…
We propose smoothed max pooling loss and its application to keyword spotting systems. The proposed approach jointly trains an encoder (to detect keyword parts) and a decoder (to detect whole keyword) in a semi-supervised manner. The…
We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an optimal segmentation.…
Sign spotting, the task of identifying and localizing individual signs within continuous sign language video, plays a pivotal role in scaling dataset annotations and addressing the severe data scarcity issue in sign language translation.…
Index is an important component in database systems. Learned indexes have been shown to outperform traditional tree-based index structures for fixed-sized integer or floating point keys. However, the application of the learned solution to…
Customizable keyword spotting (KWS) in continuous speech has attracted increasing attention due to its real-world application potential. While contrastive learning (CL) has been widely used to extract keyword representations, previous CL…
Supervised and semi-supervised semantic segmentation algorithms require significant amount of annotated data to achieve a good performance. In many situations, the data is either not available or the annotation is expensive. The objective…
In this work, we present a unified model that can handle both Keyword Spotting and Word Recognition with the same network architecture. The proposed network is comprised of a non-recurrent CTC branch and a Seq2Seq branch that is further…
Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken Language Understanding (SLU) approaches to ensure the…
One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper, we propose an on-the-fly random utterance concatenation…
As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to…
Scene text spotting is essential in various computer vision applications, enabling extracting and interpreting textual information from images. However, existing methods often neglect the spatial semantics of word images, leading to…
End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…
Accurate and stable feature matching is critical for computer vision tasks, particularly in applications such as Simultaneous Localization and Mapping (SLAM). While recent learning-based feature matching methods have demonstrated promising…
Using a vision-inspired keyword spotting framework, we propose an architecture with input-dependent dynamic depth capable of processing streaming audio. Specifically, we extend a conformer encoder with trainable binary gates that allow us…
One of the problems with automated audio captioning (AAC) is the indeterminacy in word selection corresponding to the audio event/scene. Since one acoustic event/scene can be described with several words, it results in a combinatorial…
Spoken Language Understanding (SLU) is composed of two subtasks: intent detection (ID) and slot filling (SF). There are two lines of research on SLU. One jointly tackles these two subtasks to improve their prediction accuracy, and the other…
Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…
Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance…
In this paper, we study the problem of image-text matching. Inferring the latent semantic alignment between objects or other salient stuff (e.g. snow, sky, lawn) and the corresponding words in sentences allows to capture fine-grained…
Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords. To…