Related papers: Fast, Not Fancy: Rethinking G2P with Rich Data and…
There is a growing interest in developing strong biomedical vision-language models. A popular approach to achieve robust representations is to use web-scale scientific data. However, current biomedical vision-language pretraining typically…
Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation, the task of transforming informal into formal mathematical statements. Autoformalisation helps…
Generating patent descriptions from scientific papers is challenging due to fundamental rhetorical and structural disparities between the two genres. Existing approaches treat this as surface-level rewriting, failing to capture the…
Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly…
The problem of synthetic speech detection has enjoyed considerable attention, with recent methods achieving low error rates across several established benchmarks. However, to what extent can low error rates on academic benchmarks translate…
Homonyms are words with identical spelling but distinct meanings, which pose challenges for many generative models. When a homonym appears in a prompt, diffusion models may generate multiple senses of the word simultaneously, which is known…
Generating semantically coherent and visually accurate talking faces requires bridging the gap between linguistic meaning and facial articulation. Although audio-driven methods remain prevalent, their reliance on high-quality paired audio…
Recent advances in image editing have shifted from manual pixel manipulation to employing deep learning methods like stable diffusion models, which now leverage cross-attention mechanisms for text-driven control. This transition has…
As of recent generative adversarial networks have allowed for big leaps in the realism of generated images in diverse domains, not the least of which being handwritten text generation. The generation of realistic-looking hand-written text…
Recently, the Large Language Model-based Phoneme-to-Grapheme (LLM-P2G) method has shown excellent performance in speech recognition tasks and has become a feasible direction to replace the traditional WFST decoding method. This framework…
End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain…
Deepspeech was very useful for development IoT devices that need voice recognition. One of the voice recognition systems is deepspeech from Mozilla. Deepspeech is an open-source voice recognition that was using a neural network to convert…
Multimodal Large Language Models (MLLMs) have achieved remarkable advances by integrating text, image, and audio understanding within a unified architecture. However, existing distributed training frameworks remain fundamentally data-blind:…
We propose a new homomorphic encryption scheme based on the hardness of decoding under independent random noise from certain affine families of codes. Unlike in previous lattice-based homomorphic encryption schemes, where the message is…
While deep learning systems have gained significant ground in speech enhancement research, these systems have yet to make use of the full potential of deep learning systems to provide high-level feedback. In particular, phonetic feedback is…
The most important way to achieve higher performance in computer systems is through heterogeneous computing, i.e., by adopting hardware platforms containing more than one type of processor, such as CPUs, GPUs, and FPGAs. Several types of…
An increasing number of Chinese people are troubled by different degrees of visual impairment, which has made the modal conversion between a single image or video frame in the visual field and the audio expressing the same information a…
Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired…
Current advancements in Natural Language Processing (NLP) have largely favored resource-rich languages, leaving a significant gap in high-quality datasets for low-resource languages like Hindi. This scarcity is particularly evident in text…
The rapid advancement of Large Language Models (LLMs) has spurred significant progress in Large Speech-Language Models (LSLMs), enhancing their capabilities in both speech understanding and generation. While existing LSLMs often concentrate…