Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech

Integrating human feedback to align text-to-speech (TTS) system outputs with human preferences has proven to be an effective approach for enhancing the robustness of language model-based TTS systems. Current approaches primarily focus on using preference data annotated at the utterance level. However, frequent issues that affect the listening experience often only arise in specific segments of audio samples, while other segments are well-generated. In this study, we propose a fine-grained preference optimization approach (FPO) to enhance the robustness of TTS systems. FPO focuses on addressing localized issues in generated samples rather than uniformly optimizing the entire utterance. Specifically, we first analyze the types of issues in generated samples, categorize them into two groups, and propose a selective training loss strategy to optimize preferences based on fine-grained labels for each issue type. Experimental results show that FPO enhances the robustness of zero-shot TTS systems by effectively addressing local issues, significantly reducing the bad case ratio, and improving intelligibility. Furthermore, FPO exhibits superior data efficiency compared with baseline systems, achieving similar performance with fewer training samples.

StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching

Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) current approaches primarily focus on adapting timbre from unseen speakers and are unable to transfer style and timbre to different unseen speakers independently; 2) these approaches often suffer from slower inference speeds due to the autoregressive modeling methods or the need for numerous sampling steps; 3) the quality and similarity of the converted samples are still not fully satisfactory. To address these challenges, we propose a style controllable zero-shot VC approach named StableVC, which aims to transfer timbre and style from source speech to different unseen target speakers. Specifically, we decompose speech into linguistic content, timbre, and style, and then employ a conditional flow matching module to reconstruct the high-quality mel-spectrogram based on these decomposed features. To effectively capture timbre and style in a zero-shot manner, we introduce a novel dual attention mechanism with an adaptive gate, rather than using conventional feature concatenation. With this non-autoregressive design, StableVC can efficiently capture the intricate timbre and style from different unseen speakers and generate high-quality speech significantly faster than real-time. Experiments demonstrate that our proposed StableVC outperforms state-of-the-art baseline systems in zero-shot VC and achieves flexible control over timbre and style from different unseen speakers. Moreover, StableVC offers approximately 25x and 1.65x faster sampling compared to autoregressive and diffusion-based baselines.

A Unified Platform for At-Home Post-Stroke Rehabilitation Enabled by Wearable Technologies and Artificial Intelligence

At-home rehabilitation for post-stroke patients presents significant challenges, as continuous, personalized care is often limited outside clinical settings. Additionally, the absence of comprehensive solutions addressing diverse rehabilitation needs in home environments complicates recovery efforts. Here, we introduce a smart home platform that integrates wearable sensors, ambient monitoring, and large language model (LLM)-powered assistance to provide seamless health monitoring and intelligent support. The system leverages machine learning enabled plantar pressure arrays for motor recovery assessment (94% classification accuracy), a wearable eye-tracking module for cognitive evaluation, and ambient sensors for precise smart home control (100% operational success, <1 s latency). Additionally, the LLM-powered agent, Auto-Care, offers real-time interventions, such as health reminders and environmental adjustments, enhancing user satisfaction by 29%. This work establishes a fully integrated platform for long-term, personalized rehabilitation, offering new possibilities for managing chronic conditions and supporting aging populations.

Wearable intelligent throat enables natural speech in stroke patients with dysarthria

Wearable silent speech systems hold significant potential for restoring communication in patients with speech impairments. However, seamless, coherent speech remains elusive, and clinical efficacy is still unproven. Here, we present an AI-driven intelligent throat (IT) system that integrates throat muscle vibrations and carotid pulse signal sensors with large language model (LLM) processing to enable fluent, emotionally expressive communication. The system utilizes ultrasensitive textile strain sensors to capture high-quality signals from the neck area and supports token-level processing for real-time, continuous speech decoding, enabling seamless, delay-free communication. In tests with five stroke patients with dysarthria, IT's LLM agents intelligently corrected token errors and enriched sentence-level emotional and logical coherence, achieving low error rates (4.2% word error rate, 2.9% sentence error rate) and a 55% increase in user satisfaction. This work establishes a portable, intuitive communication platform for patients with dysarthria with the potential to be applied broadly across different neurological conditions and in multi-language support systems.

Reward Modeling with Ordinal Feedback: Wisdom of the Crowd

Learning a reward model (RM) from human preferences has been an important component in aligning large language models (LLMs). The canonical setup of learning RMs from pairwise preference data is rooted in the classic Bradley-Terry (BT) model that accepts binary feedback, i.e., the label being either Response 1 is better than Response 2, or the opposite. Such a setup inevitably discards potentially useful samples (such as "tied" between the two responses) and loses more fine-grained information (such as "slightly better"). In this paper, we propose a framework for learning RMs under ordinal feedback which generalizes the case of binary preference feedback to any arbitrary granularity. Specifically, we first identify a marginal unbiasedness condition, which generalizes the assumption of the BT model in the existing binary feedback setting. The condition validates itself via the sociological concept of the wisdom of the crowd. Under the condition, we develop a natural probability model for pairwise preference data under ordinal feedback and analyze its properties. We prove the statistical benefits of ordinal feedback in terms of reducing the Rademacher complexity compared to the case of binary feedback. The proposed learning objective and the theory also extend to hinge loss and direct policy optimization (DPO). In particular, the theoretical analysis may be of independent interest when applying to a seemingly unrelated problem of knowledge distillation to interpret the bias-variance trade-off therein. The framework also sheds light on writing guidance for human annotators. Our numerical experiments validate that fine-grained feedback leads to better reward learning for both in-distribution and out-of-distribution settings. Further experiments show that incorporating a certain proportion of samples with tied preference boosts RM learning.

CTEFM-VC: Zero-Shot Voice Conversion Based on Content-Aware Timbre Ensemble Modeling and Flow Matching

Zero-shot voice conversion (VC) aims to transform the timbre of a source speaker into any previously unseen target speaker, while preserving the original linguistic content. Despite notable progress, attaining a degree of speaker similarity and naturalness on par with ground truth recordings continues to pose great challenge. In this paper, we propose CTEFM-VC, a zero-shot VC framework that leverages Content-aware Timbre Ensemble modeling and Flow Matching. Specifically, CTEFM-VC disentangles utterances into linguistic content and timbre representations, subsequently utilizing a conditional flow matching model and a vocoder to reconstruct the mel-spectrogram and waveform. To enhance its timbre modeling capability and the naturalness of generated speech, we propose a context-aware timbre ensemble modeling approach that adaptively integrates diverse speaker verification embeddings and enables the joint utilization of linguistic and timbre features through a cross-attention module. Experiments show that our CTEFM-VC system surpasses state-of-the-art VC methods in both speaker similarity and naturalness by at least 18.5% and 7.0%.

Can Language Models Enable In-Context Database?

Large language models (LLMs) are emerging as few-shot learners capable of handling a variety of tasks, including comprehension, planning, reasoning, question answering, arithmetic calculations, and more. At the core of these capabilities is LLMs' proficiency in representing and understanding structural or semi-structural data, such as tables and graphs. Numerous studies have demonstrated that reasoning on tabular data or graphs is not only feasible for LLMs but also gives a promising research direction which treats these data as in-context data. The lightweight and human readable characteristics of in-context database can potentially make it an alternative for the traditional database in typical RAG (Retrieval Augmented Generation) settings. However, almost all current work focuses on static in-context data, which does not allow dynamic update. In this paper, to enable dynamic database update, delta encoding of database is proposed. We explore how data stored in traditional RDBMS can be encoded as in-context text and evaluate LLMs' proficiency for CRUD (Create, Read, Update and Delete) operations on in-context databases. A benchmark named InConDB is presented and extensive experiments are conducted to show the performance of different language models in enabling in-context database by varying the database encoding method, prompting method, operation type and input data distribution, revealing both the proficiency and limitations.

Building Multi-Agent Copilot towards Autonomous Agricultural Data Management and Analysis

Current agricultural data management and analysis paradigms are to large extent traditional, in which data collecting, curating, integration, loading, storing, sharing and analyzing still involve too much human effort and know-how. The experts, researchers and the farm operators need to understand the data and the whole process of data management pipeline to make fully use of the data. The essential problem of the traditional paradigm is the lack of a layer of orchestrational intelligence which can understand, organize and coordinate the data processing utilities to maximize data management and analysis outcome. The emerging reasoning and tool mastering abilities of large language models (LLM) make it a potentially good fit to this position, which helps a shift from the traditional user-driven paradigm to AI-driven paradigm. In this paper, we propose and explore the idea of a LLM based copilot for autonomous agricultural data management and analysis. Based on our previously developed platform of Agricultural Data Management and Analytics (ADMA), we build a proof-of-concept multi-agent system called ADMA Copilot, which can understand user's intent, makes plans for data processing pipeline and accomplishes tasks automatically, in which three agents: a LLM based controller, an input formatter and an output formatter collaborate together. Different from existing LLM based solutions, by defining a meta-program graph, our work decouples control flow and data flow to enhance the predictability of the behaviour of the agents. Experiments demonstrates the intelligence, autonomy, efficacy, efficiency, extensibility, flexibility and privacy of our system. Comparison is also made between ours and existing systems to show the superiority and potential of our system.

Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matching

Achieving monocular camera localization within pre-built LiDAR maps can bypass the simultaneous mapping process of visual SLAM systems, potentially reducing the computational overhead of autonomous localization. To this end, one of the key challenges is cross-modal place recognition, which involves retrieving 3D scenes (point clouds) from a LiDAR map according to online RGB images. In this paper, we introduce an efficient framework to learn descriptors for both RGB images and point clouds. It takes visual state space model (VMamba) as the backbone and employs a pixel-view-scene joint training strategy for cross-modal contrastive learning. To address the field-of-view differences, independent descriptors are generated from multiple evenly distributed viewpoints for point clouds. A visible 3D points overlap strategy is then designed to quantify the similarity between point cloud views and RGB images for multi-view supervision. Additionally, when generating descriptors from pixel-level features using NetVLAD, we compensate for the loss of geometric information, and introduce an efficient scheme for multi-view generation. Experimental results on the KITTI and KITTI-360 datasets demonstrate the effectiveness and generalization of our method. The code will be released upon acceptance.

Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling

Zero-shot voice conversion (VC) aims to transform the source speaker timbre into an arbitrary unseen one without altering the original speech content.While recent advancements in zero-shot VC methods have shown remarkable progress, there still remains considerable potential for improvement in terms of improving speaker similarity and speech naturalness.In this paper, we propose Takin-VC, a novel zero-shot VC framework based on jointly hybrid content and memory-augmented context-aware timbre modeling to tackle this challenge. Specifically, an effective hybrid content encoder, guided by neural codec training, that leverages quantized features from pre-trained WavLM and HybridFormer is first presented to extract the linguistic content of the source speech. Subsequently, we introduce an advanced cross-attention-based context-aware timbre modeling approach that learns the fine-grained, semantically associated target timbre features. To further enhance both speaker similarity and real-time performance, we utilize a conditional flow matching model to reconstruct the Mel-spectrogram of the source speech. Additionally, we advocate an efficient memory-augmented module designed to generate high-quality conditional target inputs for the flow matching process, thereby improving the overall performance of the proposed system. Experimental results demonstrate that the proposed Takin-VC method surpasses state-of-the-art zero-shot VC systems, delivering superior performance in terms of both speech naturalness and speaker similarity.