Related papers: ShrinkML: End-to-End ASR Model Compression Using R…
Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM) approach that…
Large Reasoning Language Models (LRLMs or LRMs) demonstrate remarkable capabilities in complex reasoning tasks, but suffer from significant computational inefficiencies due to overthinking phenomena. Existing efficient reasoning methods…
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…
End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…
This study addresses a gap in the utilization of Reinforcement Learning (RL) and Machine Learning (ML) techniques in solving the Stochastic Vehicle Routing Problem (SVRP) that involves the challenging task of optimizing vehicle routes under…
Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…
Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in…
Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms and…
Large language models (LLMs) excel at language understanding and generation, but their enormous computational and memory requirements hinder deployment. Compression offers a potential solution to mitigate these constraints. However, most…
Adapting Automatic Speech Recognition (ASR) models to new domains results in a deterioration of performance on the original domain(s), a phenomenon called Catastrophic Forgetting (CF). Even monolingual ASR models cannot be extended to new…
In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many…
We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up…
Recent achievements in end-to-end deep learning have encouraged the exploration of tasks dealing with highly structured data with unified deep network models. Having such models for compressing audio signals has been challenging since it…
In this paper, we start by training End-to-End Automatic Speech Recognition (ASR) models using Federated Learning (FL) and examining the fundamental considerations that can be pivotal in minimizing the performance gap in terms of word error…
Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM…
The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-of-the-art ASR. Despite LLMs being trained with an extensive…
Mixture-of-experts (MoE) models have achieved excellent results in many tasks. However, conventional MoE models are often very large, making them challenging to deploy on resource-constrained edge devices. In this paper, we propose a novel…
While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific…
Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent advances in speech…
In this paper, we present a novel modeling method for single-channel multi-talker overlapped automatic speech recognition (ASR) systems. Fully neural network based end-to-end models have dramatically improved the performance of multi-taker…