Related papers: Lattice Rescoring Based on Large Ensemble of Compl…

Language models (LM) play an important role in large vocabulary continuous speech recognition (LVCSR). However, traditional language models only predict next single word with given history, while the consecutive predictions on a sequence of…

Automatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the performance of downstream tasks like summarization. This issue is particularly pronounced…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

This research proposes the interaction loop model "ASR-LLMs-Smart Glasses", which model combines automatic speech recognition, large language model and smart glasses to facilitate seamless human-computer interaction. And the methodology of…

Goal-oriented conversational interfaces are designed to accomplish specific tasks and typically have interactions that tend to span multiple turns adhering to a pre-defined structure and a goal. However, conventional neural language models…

Automatic Speech Recognition (ASR) systems remain prone to errors that affect downstream applications. In this paper, we propose LIR-ASR, a heuristic optimized iterative correction framework using LLMs, inspired by human auditory…

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…

Large language models (LLMs) often struggle to perform multi-target reasoning in long-context scenarios where relevant information is scattered across extensive documents. To address this challenge, we introduce NeuroSymbolic Augmented…

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…

This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to…

Despite rapid advances in large language models (LLMs), their integration with traditional supervised machine learning (ML) techniques that have proven applicability to medical data remains underexplored. This is particularly true for…

We investigate the use of large language models (LLMs) as post-processing modules for automatic speech recognition (ASR), focusing on their ability to perform error correction for disordered speech. In particular, we propose…

Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…

Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which aims to predict the ground-truth transcription from the decoded N-best hypotheses. Thanks to the…

As large language models (LLMs) grow in parameter size and capabilities, such as interaction through prompting, they open up new ways of interfacing with automatic speech recognition (ASR) systems beyond rescoring n-best lists. This work…

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model size scaling, and deep integration with large language models (LLMs). However, LLMs…

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.…

Sequence-to-sequence models with an implicit alignment mechanism (e.g. attention) are closing the performance gap towards traditional hybrid hidden Markov models (HMM) for the task of automatic speech recognition. One important factor to…

Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To…