Related papers: Dialogue Act Recognition via CRF-Attentive Structu…
We introduce DAS (Domain Adaptation with Synthetic data), a novel domain adaptation framework for pre-trained ASR model, designed to efficiently adapt to various language-defined domains without requiring any real data. In particular, DAS…
As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the…
Complex Event Recognition and Forecasting (CER/F) techniques attempt to detect, or even forecast ahead of time, event occurrences in streaming input using predefined event patterns. Such patterns are not always known in advance, or they…
Unsupervised domain adaptation (UDA) aims to learn transferable knowledge from a labeled source domain and adapts a trained model to an unlabeled target domain. To bridge the gap between source and target domains, one prevailing strategy is…
Compared with individual agents, large language model based multi-agent systems have shown great capabilities consistently across diverse tasks, including code generation, mathematical reasoning, and planning, etc. Despite their impressive…
Specialized visual tools can augment large language models or vision language models with expert knowledge (e.g., grounding, spatial reasoning, medical knowledge, etc.), but knowing which tools to call (and when to call them) can be…
Sentence matching is a fundamental task of natural language processing with various applications. Most recent approaches adopt attention-based neural models to build word- or phrase-level alignment between two sentences. However, these…
Phoneme recognition is a largely unsolved problem in NLP, especially for low-resource languages like Urdu. The systems that try to extract the phonemes from audio speech require hand-labeled phonetic transcriptions. This requires expert…
Speech recognition systems have improved dramatically over the last few years, however, their performance is significantly degraded for the cases of accented or impaired speech. This work explores domain adversarial neural networks (DANN)…
Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of…
Developing and selecting hearing aids is a time consuming process which is simplified by using objective models. Previously, the framework for auditory discrimination experiments (FADE) accurately simulated benefits of hearing aid…
Learning an effective speaker representation is crucial for achieving reliable performance in speaker verification tasks. Speech signals are high-dimensional, long, and variable-length sequences containing diverse information at each…
Open domain dialog systems face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that by conditioning the response generation on interpretable discrete dialog attributes and composed…
This paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames. While previous works have made significant…
While image captioning through machines requires structured learning and basis for interpretation, improvement requires multiple context understanding and processing in a meaningful way. This research will provide a novel concept for…
Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based…
Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions…
Natural Language Inference (NLI), also known as Recognizing Textual Entailment (RTE), is one of the most important problems in natural language processing. It requires to infer the logical relationship between two given sentences. While…
Dialogue State Tracking (DST) is a key part of task-oriented dialogue systems, identifying important information in conversations. However, its accuracy drops significantly in spoken dialogue environments due to named entity errors from…
Speaker-role diarization (RD), such as doctor vs. patient or lawyer vs. client, is practically often more useful than conventional speaker diarization (SD), which assigns only generic labels (speaker-1, speaker-2). The state-of-the-art…