Related papers: From Text to Forecasts: Bridging Modality Gap with…
We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…
Existing time series forecasting methods primarily rely on the numerical data itself. However, real-world time series exhibit complex patterns associated with multimodal information, making them difficult to predict with numerical data…
The proliferation of time series foundation models has created a landscape where no single method achieves consistent superiority, framing the central challenge not as finding the best model, but as orchestrating an optimal ensemble with…
Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…
Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring. Recent studies have revealed that Large Language Models (LLMs), with their powerful in-contextual modeling capabilities,…
Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…
Multimodal semantic segmentation benefits remote sensing analysis by combining complementary information from different sensor modalities. In real-world remote sensing applications, one or more modalities may be unavailable due to sensor…
Most knowledge graph completion (KGC) methods learn latent representations of entities and relations of a given graph by mapping them into a vector space. Although the majority of these methods focus on static knowledge graphs, a large…
Multimodal time series forecasting is crucial in real-world applications, where decisions depend on both numerical data and contextual signals. The core challenge is to effectively combine temporal numerical patterns with the context…
The style transfer task in Text-to-Speech refers to the process of transferring style information into text content to generate corresponding speech with a specific style. However, most existing style transfer approaches are either based on…
Recent advances in text-to-speech (TTS) technology have enabled systems to generate speech that is often indistinguishable from human speech, bringing benefits to accessibility, content creation, and human-computer interaction. However,…
We propose a novel causal prosody mediation framework for expressive text-to-speech (TTS) synthesis. Our approach augments the FastSpeech2 architecture with explicit emotion conditioning and introduces counterfactual training objectives to…
While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i)…
Recent advancements in Large Language Models (LLMs) have the potential to transform financial analytics by integrating numerical and textual data. However, challenges such as insufficient context when fusing multimodal information and the…
Temporal distribution shift (TDS) erodes the long-term accuracy of recommender systems, yet industrial practice still relies on periodic incremental training, which struggles to capture both stable and transient patterns. Existing…
Salient Span Masking (SSM) has shown itself to be an effective strategy to improve closed-book question answering performance. SSM extends general masked language model pretraining by creating additional unsupervised training sentences that…
Multi-modality spatio-temporal (MoST) data extends spatio-temporal (ST) data by incorporating multiple modalities, which is prevalent in monitoring systems, encompassing diverse traffic demands and air quality assessments. Despite…
Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural network architectures rather than persons. This type of…
In this paper, we present a novel method for measurably adjusting the semantics of text while preserving its sentiment and fluency, a task we call semantic text exchange. This is useful for text data augmentation and the semantic correction…
Detecting lexical semantic change in smaller data sets, e.g. in historical linguistics and digital humanities, is challenging due to a lack of statistical power. This issue is exacerbated by non-contextual embedding models that produce one…