Related papers: Align2Speak: Improving TTS for Low Resource Langua…

Conversational Recommender Systems (CRSs) leverage natural language interactions for personalized recommendation, yet information-scarce dialogue histories and single-turn recommendation paradigms may severely hinder accurate modeling of…

Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the generative potential of diffusion-based T2V models. We present…

Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model:…

While recent neural text-to-speech (TTS) systems perform remarkably well, they typically require a substantial amount of recordings from the target speaker reading in the desired speaking style. In this work, we present a novel 3-step…

Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to train these models.…

Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training methods, like Reinforcement Learning with Human Feedback (RLHF),…

Our goal is to enable large language models (LLMs) to balance multiple human preference dimensions; such as helpfulness, safety, and verbosity, through principled and controllable alignment. Existing preference optimization methods,…

Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been…

Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address…

Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks…

When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies…

Improving the alignment of language models with human preferences remains an active research challenge. Previous approaches have primarily utilized Reinforcement Learning from Human Feedback (RLHF) via online RL methods such as Proximal…

We present ALT (ALignment with Textual feedback), an approach that aligns language models with user preferences expressed in text. We argue that text offers greater expressiveness, enabling users to provide richer feedback than simple…

Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-thought (CoT). As a crucial component for developing these…

Augmenting the training data of automatic speech recognition (ASR) systems with synthetic data generated by text-to-speech (TTS) or voice conversion (VC) has gained popularity in recent years. Several works have demonstrated improvements in…

The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to…

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically employ off-policy…

We present SignDPO, a novel multi-level Direct Preference Optimisation (DPO) framework designed to enhance the alignment of skeleton-based Sign Language Translation. While current skeleton-based models have made significant progress using…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an important paradigm for unlocking reasoning capabilities in large language models, exemplified by the success of OpenAI o1 and DeepSeek-R1. Currently, Group Relative…