Related papers: Gradual Soundness: Lessons from Static Python
Gradually typed programming languages, which allow for soundly mixing static and dynamically typed programming styles, present a strong challenge for metatheorists. Even the simplest sound gradually typed languages feature at least…
Python has become the de facto language for scientific computing. Programming in Python is highly productive, mainly due to its rich science-oriented software ecosystem built around the NumPy module. As a result, the demand for Python…
Session types express and enforce safe communication in concurrent message-passing systems by statically capturing the interaction protocols between processes in the type. Recent works extend session types with arithmetic refinements, which…
Many object-oriented dynamic languages allow programmers to _extract methods_ from objects and treat them as functions. This allows for flexible programming patterns, but presents challenges for type systems. In particular, a simple…
Large language models trained on code have shown great potential to increase productivity of software developers. Several execution-based benchmarks have been proposed to evaluate functional correctness of model-generated code on simple…
Discrete prompts have been used for fine-tuning Pre-trained Language Models for diverse NLP tasks. In particular, automatic methods that generate discrete prompts from a small set of training instances have reported superior performance.…
Single-stage text-to-speech models have been actively studied recently, and their results have outperformed two-stage pipeline systems. Although the previous single-stage model has made great progress, there is room for improvement in terms…
In the field of data science, and for academics in general, the Python programming language is a popular choice, mainly because of its libraries for storing, manipulating, and gaining insight from data. Evidence includes the versatile set…
We present a logically principled foundation for systematizing, in a way that works with any computational effect and evaluation order, SMT constraint generation seen in refinement type systems for functional programming languages. By…
Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models…
Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…
In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS…
TypeShift is a tool for visualizing linguistic patterns in the timing of typing production. Language production is a complex process which draws on linguistic, cognitive and motor skills. By visualizing holistic trends in the typing…
We present a training method with linguistic speech regularization that improves the robustness of spontaneous speech synthesis methods with filled pause (FP) insertion. Spontaneous speech synthesis is aimed at producing speech with…
We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent…
Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…
Coroutine, as a powerful programming construct, is widely used in asynchronous applications to replace thread-based programming or the callback hell. Using coroutines makes code more readable and maintainable, for its ability to transfer…
Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers for resource-constrained research teams. In this report, we…
Gradually typed languages allow statically typed and dynamically typed code to interact while maintaining benefits of both styles. The key to reasoning about these mixed programs is Siek-Vitousek-Cimini-Boyland's (dynamic) gradual…
Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that…