Graduate students
Artyom Stitsyuk
MS/PhD student (21.09 ~ )
5 notes
Research
2025
Counterfactual Activation Editing
A model-agnostic approach for inference-time control of prosody and pronunciation in pretrained text-to-speech systems.
2025
Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models
Recent advances in Text-to-Speech (TTS) have significantly improved speech naturalness, increasing the demand for precise prosody control and mispronunciation correction. Existing approaches for prosody manipulation often depend on specialized modules or additional training, limiting their capacity for post-hoc adjustments. Similarly, traditional mispronunciation correction relies on grapheme-to-phoneme dictionaries, making it less practical in low-resource settings. We introduce Counterfactual Activation Editing, a model-agnostic method that manipulates internal representations in a pre-trained TTS model to achieve post-hoc control of prosody and pronunciation. Experimental results show that our method effectively adjusts prosodic features and corrects mispronunciations while preserving synthesis quality. This opens the door to inference-time refinement of TTS outputs without retraining, bridging the gap between pre-trained TTS models and editable speech synthesis.
2025
xPatch
A dual-stream time-series forecasting architecture combines exponential decomposition, an MLP linear stream, and a CNN nonlinear stream.
2025
xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition
In this work, we design eXponential Patch (xPatch for short), a novel dual-stream architecture that utilizes exponential decomposition. Inspired by the classical exponential smoothing approaches, xPatch introduces the innovative seasonal-trend exponential decomposition module. Additionally, we propose a dual-flow architecture that consists of an MLP-based linear stream and a CNN-based non-linear stream. This model investigates the benefits of employing patching and channel-independence techniques within a non-transformer model. Finally, we develop a robust arctangent loss function and a sigmoid learning rate adjustment scheme, which prevent overfitting and boost forecasting performance.
2023
Explainable AI-Based Interface System for Weather Forecasting Model
As machine learning (ML) becomes more prevalent in meteorological decision-making, user-centered explainable artificial intelligence (XAI) studies have yet to extend into this domain. This study identifies three key requirements for explaining black-box models in meteorology: model bias in different rainfall scenarios, model reasoning, and output confidence. Appropriate XAI methods are mapped to these requirements and evaluated both quantitatively and qualitatively. The results show that intuitive explanations improve decision-making utility and user trust, highlighting the need for user-centered XAI to enhance the usability of AI systems in practice.
4 papers
Publications
2025
- [100]
Deep-DFVAR: Dynamic Factor Vector Autoregression with Deep Learning for Regional House Price Index Forecasting
- [96]
Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models
- [88]
xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition