相关论文: Textless NLP -- Zero Resource Challenge with Low R…

Integrating audio comprehension and generation into large language models (LLMs) remains challenging due to the continuous nature of audio and the resulting high sampling rates. Here, we introduce a novel approach that combines Variational…

Despite remarkable advancements in recent voice conversion (VC) systems, enhancing speaker similarity in zero-shot scenarios remains challenging. This challenge arises from the difficulty of generalizing and adapting speaker characteristics…

Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…

While recent neural audio codecs deliver superior speech quality at ultralow bitrates over traditional methods, their practical adoption is hindered by obstacles related to low-resource operation and robustness to acoustic distortions. Edge…

Tensor program tuning is a non-convex objective optimization problem, to which search-based approaches have proven to be effective. At the core of the search-based approaches lies the design of the cost model. Though deep learning-based…

Speech-to-singing voice conversion (STS) task always suffers from data scarcity, because it requires paired speech and singing data. Compounding this issue are the challenges of content-pitch alignment and the suboptimal quality of…

Recent years have witnessed the emergence of textual commonsense knowledge bases, aimed at providing more nuanced and context-rich knowledge. The integration of external commonsense into language models has been shown to be a key enabler in…

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

Transformer based architectures have shown notable results on many down streaming tasks including question answering. The availability of data, on the other hand, impedes obtaining legitimate performance for low-resource languages. In this…

This paper addresses the problem of improving speech recognition accuracy with lattice rescoring in low-resource languages where the baseline language model is insufficient for generating inclusive lattices. We minimally augment the…

Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale…

Training Large Language Models (LLMs) with Group Relative Policy Optimization (GRPO) encounters a significant challenge: models often fail to produce accurate responses, particularly in small-scale architectures. This limitation not only…

Bangla -- ranked as the 6th most widely spoken language across the world (https://www.ethnologue.com/guides/ethnologue200), with 230 million native speakers -- is still considered as a low-resource language in the natural language…

Large Language Models (LLMs) have become a popular choice for many Natural Language Processing (NLP) tasks due to their versatility and ability to produce high-quality results. Specifically, they are increasingly used for automatic code…

We present software that, in only a few hours, transcribes forty hours of recorded speech in a surprise language, using only a few tens of megabytes of noisy text in that language, and a zero-resource grapheme to phoneme (G2P) table. A…

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

Neural codec language model (LM) has demonstrated strong capability in zero-shot text-to-speech (TTS) synthesis. However, the codec LM often suffers from limitations in inference speed and stability, due to its auto-regressive nature and…

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…

Attention encoder-decoder model architecture is the backbone of several recent top performing foundation speech models: Whisper, Seamless, OWSM, and Canary-1B. However, the reported data and compute requirements for their training are…

Recently, very large language models (LLMs) have shown exceptional performance on several English NLP tasks with just in-context learning (ICL), but their utility in other languages is still underexplored. We investigate their effectiveness…