Search Results for author:
Found 19 papers, 2 papers with code
Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development
Overall, we demonstrate the effectiveness of our optimization method for role-based multi-agent systems tackling software development tasks evaluated on diverse evaluation dimensions, and we investigate the impact of diverse optimization settings on group behaviors of the multi-agent systems to provide practical insights for future development.
MemInsight: Autonomous Memory Augmentation for LLM Agents
In this work, we propose an autonomous memory augmentation approach, MemInsight, to enhance semantic data representation and retrieval mechanisms.
A Study on Leveraging Search and Self-Feedback for Agent Reasoning
In this study, we investigate how search and model's self-feedback can be leveraged for reasoning tasks.
TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues
Temporal reasoning in multi-session dialogues presents a significant challenge which has been under-studied in previous temporal reasoning benchmarks.
Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications
For coordination capabilities, we demonstrate the effectiveness of inter-agent communication and payload referencing mechanisms, achieving end-to-end goal success rates of 90%.
RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration
Through controlled experiments, we analyze how different voting rules affect decision quality and efficiency in a multi-round collaboration.
Inference time LLM alignment in single and multidomain preference spectrum
Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure.
CERET: Cost-Effective Extrinsic Refinement for Text Generation
Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt.
SpeechVerse: A Large-scale Generalizable Audio Language Model
The models are instruction finetuned using continuous latent representations extracted from the speech foundation model to achieve optimal zero-shot performance on a diverse range of speech processing tasks using natural language instructions.
Masked Audio Text Encoders are Effective Multi-Modal Rescorers
Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Mask The Bias: Improving Domain-Adaptive Generalization of CTC-based ASR with Internal Language Model Estimation
Internal language model estimation (ILME) has been proposed to mitigate this bias for autoregressive models such as attention-based encoder-decoder and RNN-T.
Adaptation Approaches for Nearest Neighbor Language Models
Semi-parametric Nearest Neighbor Language Models ($k$NN-LMs) have produced impressive gains over purely parametric LMs, by leveraging large-scale neighborhood retrieval over external memory datastores.
Towards Personalization of CTC Speech Recognition Models with Contextual Adapters and Adaptive Boosting
End-to-end speech recognition models trained using joint Connectionist Temporal Classification (CTC)-Attention loss have gained popularity recently.
Remember the context! ASR slot error correction through memorization
Accurate recognition of slot values such as domain specific words or named entities by automatic speech recognition (ASR) systems forms the core of the Goal-oriented Dialogue Systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Adapting Long Context NLM for ASR Rescoring in Conversational Agents
Neural Language Models (NLM), when trained and evaluated with context spanning multiple utterances, have been shown to consistently outperform both conventional n-gram language models and NLMs that use limited context.
Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning
Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech.
Neural Inverse Text Normalization
We propose an efficient and robust neural solution for ITN leveraging transformer based seq2seq models and FST-based text normalization techniques for data preparation.
Multimodal Semi-supervised Learning Framework for Punctuation Prediction in Conversational Speech
Experiments conducted on the Fisher corpus show that our proposed approach achieves ~6-9% and ~3-4% absolute improvement (F1 score) over the baseline BLSTM model on reference transcripts and ASR outputs respectively.
Robust Prediction of Punctuation and Truecasing for Medical ASR
We also present techniques for domain and task specific adaptation by fine-tuning masked language models with medical domain data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
