Hema Swetha Koppula

Karren Yang, Ting-Yao Hu, Jen-Hao Rick Chang et al.

Adapting generic speech recognition models to specific individuals is a challenging problem due to the scarcity of personalized data. Recent works have proposed boosting the amount of training data using personalized text-to-speech synthesis. Here, we ask two fundamental questions about this strategy: when is synthetic data effective for personalization, and why is it effective in those cases? To address the first question, we adapt a state-of-the-art automatic speech recognition (ASR) model to target speakers from four benchmark datasets representative of different speaker types. We show that ASR personalization with synthetic data is effective in all cases, but particularly when (i) the target speaker is underrepresented in the global data, and (ii) the capacity of the global model is limited. To address the second question of why personalized synthetic data is effective, we use controllable speech synthesis to generate speech with varied styles and content. Surprisingly, we find that the text content of the synthetic data, rather than style, is important for speaker adaptation. These results lead us to propose a data selection strategy for ASR personalization based on speech content.

Hsuan Su, Ting-Yao Hu, Hema Swetha Koppula et al.

While Automatic Speech Recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to new domains and need to be finetuned on data from these domains. However, target-domain data usually are not readily available in many scenarios. In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains. To accomplish this, we propose a novel data synthesis pipeline that uses a Large Language Model (LLM) to generate a target domain text corpus, and a state-of-the-art controllable speech synthesis model to generate the corresponding speech. We propose a simple yet effective in-context instruction finetuning strategy to increase the effectiveness of LLM in generating text corpora for new domains. Experiments on the SLURP dataset show that the proposed method achieves an average relative word error rate improvement of $28\%$ on unseen target domains without any performance drop in source domains.

Tian Qin, Felix Bai, Ting-Yao Hu et al.

Real-world large language model (LLM) agents must master strategic tool use and user preference optimization through multi-turn interactions to assist users with complex planning tasks. We introduce COMPASS (Constrained Optimization through Multi-turn Planning and Strategic Solutions), a benchmark that evaluates agents on realistic travel-planning scenarios. We cast travel planning as a constrained preference optimization problem, where agents must satisfy hard constraints while simultaneously optimizing soft user preferences. To support this, we build a realistic travel database covering transportation, accommodation, and ticketing for 20 U.S. National Parks, along with a comprehensive tool ecosystem that mirrors commercial booking platforms. Evaluating state-of-the-art models, we uncover two critical gaps: (i) an acceptable-optimal gap, where agents reliably meet constraints but fail to optimize preferences, and (ii) a plan-coordination gap, where performance collapses on multi-service (flight and hotel) coordination tasks, especially for open-source models. By grounding reasoning and planning in a practical, user-facing domain, COMPASS provides a benchmark that directly measures an agent's ability to optimize user preferences in realistic tasks, bridging theoretical advances with real-world impact.

Yen-Ju Lu, Ting-Yao Hu, Hema Swetha Koppula et al.

In this work, we propose Mutual Reinforcing Data Synthesis (MRDS) within LLMs to improve few-shot dialogue summarization task. Unlike prior methods that require external knowledge, we mutually reinforce the LLMś dialogue synthesis and summarization capabilities, allowing them to complement each other during training and enhance overall performances. The dialogue synthesis capability is enhanced by directed preference optimization with preference scoring from summarization capability. The summarization capability is enhanced by the additional high quality dialogue-summary paired data produced by the dialogue synthesis capability. By leveraging the proposed MRDS mechanism, we elicit the internal knowledge of LLM in the format of synthetic data, and use it to augment the few-shot real training dataset. Empirical results demonstrate that our method improves dialogue summarization, achieving a 1.5% increase in ROUGE scores and a 0.3% improvement in BERT scores in few-shot settings. Furthermore, our method attains the highest average scores in human evaluations, surpassing both the pre-trained models and the baselines fine-tuned solely for summarization tasks.

Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari et al.

Large Language Models (LLMs) often suffer from hallucinations: output content that is not grounded in the input context, when performing long-form text generation tasks such as summarization. Prior works have shown that hallucinations can be reduced by iteratively critiquing and refining previously generated outputs using either the same model or a more powerful teacher model as the critique. However, these approaches either require additional test-time compute or assume access to more powerful teacher models, making them costly and less practical. In this work, we propose Self Critique and Refinement-based Preference Optimization (SCRPO), which is a self-supervised training framework that first constructs a preference dataset by leveraging the LLM's own critique and refinement capabilities, and then applies preference learning to improve the same LLM for faithful summarization. Experiments on three summarization benchmarks (XSUM CNNDM and SAMSum), demonstrate that our approach outperforms state-of-the-art self-supervised learning methods in terms of faithfulness metrics while either maintaining or improving other metrics that measure the overall quality of the summary. Moreover, compared to test-time refinement, our approach not only improves efficiency but also results in more faithful summaries.

Hsuan Su, Ting-Yao Hu, Hema Swetha Koppula et al.

Large language models (LLMs) often generate hallucinations -- unsupported content that undermines reliability. While most prior works frame hallucination detection as a binary task, many real-world applications require identifying hallucinated spans, which is a multi-step decision making process. This naturally raises the question of whether explicit reasoning can help the complex task of detecting hallucination spans. To answer this question, we first evaluate pretrained models with and without Chain-of-Thought (CoT) reasoning, and show that CoT reasoning has the potential to generate at least one correct answer when sampled multiple times. Motivated by this, we propose RL4HS, a reinforcement learning framework that incentivizes reasoning with a span-level reward function. RL4HS builds on Group Relative Policy Optimization and introduces Class-Aware Policy Optimization to mitigate reward imbalance issue. Experiments on the RAGTruth benchmark (summarization, question answering, data-to-text) show that RL4HS surpasses pretrained reasoning models and supervised fine-tuning, demonstrating the necessity of reinforcement learning with span-level rewards for detecting hallucination spans.

Ting-Yao Hu, Mohammadreza Armandpour, Ashish Shrivastava et al.

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthetic data is not trivial due to the gap between the synthetic and the real data distributions. Synthetic datasets may contain artifacts that do not exist in real data such as structured noise, content errors, or unrealistic speaking styles. Moreover, the synthesis process may introduce a bias due to uneven sampling of the data manifold. We propose two novel techniques during training to mitigate the problems due to the distribution gap: (i) a rejection sampling algorithm and (ii) using separate batch normalization statistics for the real and the synthetic samples. We show that these methods significantly improve the training of speech recognition models using synthetic data. We evaluate the proposed approach on keyword detection and Automatic Speech Recognition (ASR) tasks, and observe up to 18% and 13% relative error reduction, respectively, compared to naively using the synthetic data.

Jen-Hao Rick Chang, Ashish Shrivastava, Hema Swetha Koppula et al.

Controllable generative sequence models with the capability to extract and replicate the style of specific examples enable many applications, including narrating audiobooks in different voices, auto-completing and auto-correcting written handwriting, and generating missing training samples for downstream recognition tasks. However, under an unsupervised-style setting, typical training algorithms for controllable sequence generative models suffer from the training-inference mismatch, where the same sample is used as content and style input during training but unpaired samples are given during inference. In this paper, we tackle the training-inference mismatch encountered during unsupervised learning of controllable generative sequence models. The proposed method is simple yet effective, where we use a style transformation module to transfer target style information into an unrelated style input. This method enables training using unpaired content and style samples and thereby mitigate the training-inference mismatch. We apply style equalization to text-to-speech and text-to-handwriting synthesis on three datasets. We conduct thorough evaluation, including both quantitative and qualitative user studies. Our results show that by mitigating the training-inference mismatch with the proposed style equalization, we achieve style replication scores comparable to real data in our user studies.

Ting-Yao Hu, Ashish Shrivastava, Jen-Hao Rick Chang et al.

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all samples. We hypothesize that a hard sample with high training loss already provides strong training signal to update the model parameters and should be perturbed with mild or no augmentation. Perturbing a hard sample with a strong augmentation may also make it too hard to learn from. Furthermore, a sample with low training loss should be perturbed by a stronger augmentation to provide more robustness to a variety of conditions. To formalize these intuitions, we propose a novel method to learn a Sample-Adaptive Policy for Augmentation -- SapAugment. Our policy adapts the augmentation parameters based on the training loss of the data samples. In the example of Gaussian noise, a hard sample will be perturbed with a low variance noise and an easy sample with a high variance noise. Furthermore, the proposed method combines multiple augmentation methods into a methodical policy learning framework and obviates hand-crafting augmentation parameters by trial-and-error. We apply our method on an automatic speech recognition (ASR) task, and combine existing and novel augmentations using the proposed framework. We show substantial improvement, up to 21% relative reduction in word error rate on LibriSpeech dataset, over the state-of-the-art speech augmentation method.

Ashesh Jain, Hema S Koppula, Shane Soh et al.

Advanced Driver Assistance Systems (ADAS) have made driving safer over the last decade. They prepare vehicles for unsafe road conditions and alert drivers if they perform a dangerous maneuver. However, many accidents are unavoidable because by the time drivers are alerted, it is already too late. Anticipating maneuvers beforehand can alert drivers before they perform the maneuver and also give ADAS more time to avoid or prepare for the danger. In this work we propose a vehicular sensor-rich platform and learning algorithms for maneuver anticipation. For this purpose we equip a car with cameras, Global Positioning System (GPS), and a computing device to capture the driving context from both inside and outside of the car. In order to anticipate maneuvers, we propose a sensory-fusion deep learning architecture which jointly learns to anticipate and fuse multiple sensory streams. Our architecture consists of Recurrent Neural Networks (RNNs) that use Long Short-Term Memory (LSTM) units to capture long temporal dependencies. We propose a novel training procedure which allows the network to predict the future given only a partial temporal context. We introduce a diverse data set with 1180 miles of natural freeway and city driving, and show that we can anticipate maneuvers 3.5 seconds before they occur in real-time with a precision and recall of 90.5\% and 87.4\% respectively.

Ashesh Jain, Avi Singh, Hema S Koppula et al.

Anticipating the future actions of a human is a widely studied problem in robotics that requires spatio-temporal reasoning. In this work we propose a deep learning approach for anticipation in sensory-rich robotics applications. We introduce a sensory-fusion architecture which jointly learns to anticipate and fuse information from multiple sensory streams. Our architecture consists of Recurrent Neural Networks (RNNs) that use Long Short-Term Memory (LSTM) units to capture long temporal dependencies. We train our architecture in a sequence-to-sequence prediction manner, and it explicitly learns to predict the future given only a partial temporal context. We further introduce a novel loss layer for anticipation which prevents over-fitting and encourages early anticipation. We use our architecture to anticipate driving maneuvers several seconds before they happen on a natural driving data set of 1180 miles. The context for maneuver anticipation comes from multiple sensors installed on the vehicle. Our approach shows significant improvement over the state-of-the-art in maneuver anticipation by increasing the precision from 77.4% to 90.5% and recall from 71.2% to 87.4%.

Ashesh Jain, Hema S. Koppula, Bharad Raghavan et al.

Advanced Driver Assistance Systems (ADAS) have made driving safer over the last decade. They prepare vehicles for unsafe road conditions and alert drivers if they perform a dangerous maneuver. However, many accidents are unavoidable because by the time drivers are alerted, it is already too late. Anticipating maneuvers beforehand can alert drivers before they perform the maneuver and also give ADAS more time to avoid or prepare for the danger. In this work we anticipate driving maneuvers a few seconds before they occur. For this purpose we equip a car with cameras and a computing device to capture the driving context from both inside and outside of the car. We propose an Autoregressive Input-Output HMM to model the contextual information alongwith the maneuvers. We evaluate our approach on a diverse data set with 1180 miles of natural freeway and city driving and show that we can anticipate maneuvers 3.5 seconds before they occur with over 80\% F1-score in real-time.

Ashutosh Saxena, Ashesh Jain, Ozan Sener et al.

In this paper we introduce a knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks. Building such an engine brings with it the challenge of dealing with multiple data modalities including symbols, natural language, haptic senses, robot trajectories, visual features and many others. The \textit{knowledge} stored in the engine comes from multiple sources including physical interactions that robots have while performing tasks (perception, planning and control), knowledge bases from the Internet and learned representations from several robotics research groups. We discuss various technical aspects and associated challenges such as modeling the correctness of knowledge, inferring latent information and formulating different robotic tasks as queries to the knowledge engine. We describe the system architecture and how it supports different mechanisms for users and robots to interact with the engine. Finally, we demonstrate its use in three important research areas: grounding natural language, perception, and planning, which are the key building blocks for many robotic tasks. This knowledge engine is a collaborative effort and we call it RoboBrain.

Hema Swetha Koppula, Rudhir Gupta, Ashutosh Saxena

Understanding human activities and object affordances are two very important skills, especially for personal robots which operate in human environments. In this work, we consider the problem of extracting a descriptive labeling of the sequence of sub-activities being performed by a human, and more importantly, of their interactions with the objects in the form of associated affordances. Given a RGB-D video, we jointly model the human activities and object affordances as a Markov random field where the nodes represent objects and sub-activities, and the edges represent the relationships between object affordances, their relations with sub-activities, and their evolution over time. We formulate the learning problem using a structural support vector machine (SSVM) approach, where labelings over various alternate temporal segmentations are considered as latent variables. We tested our method on a challenging dataset comprising 120 activity videos collected from 4 subjects, and obtained an accuracy of 79.4% for affordance, 63.4% for sub-activity and 75.0% for high-level activity labeling. We then demonstrate the use of such descriptive labeling in performing assistive tasks by a PR2 robot.

Hema Swetha Koppula, Rudhir Gupta, Ashutosh Saxena

Human activities comprise several sub-activities performed in a sequence and involve interactions with various objects. This makes reasoning about the object affordances a central task for activity recognition. In this work, we consider the problem of jointly labeling the object affordances and human activities from RGB-D videos. We frame the problem as a Markov Random Field where the nodes represent objects and sub-activities, and the edges represent the relationships between object affordances, their relations with sub-activities, and their evolution over time. We formulate the learning problem using a structural SVM approach, where labeling over various alternate temporal segmentations are considered as latent variables. We tested our method on a dataset comprising 120 activity videos collected from four subjects, and obtained an end-to-end precision of 81.8% and recall of 80.0% for labeling the activities.