Related papers: Statistical Modeling in Continuous Speech Recognit…

Hidden Markov models (HMMs) have been successfully applied to automatic speech recognition for more than 35 years in spite of the fact that a key HMM assumption -- the statistical independence of frames -- is obviously violated by speech…

Automatic Speech Recognition (ASR) has undergone a profound transformation over the past decade, driven by advances in deep learning. This survey provides a comprehensive overview of the modern era of ASR, charting its evolution from…

To transcribe speech, automatic speech recognition systems use statistical methods, particularly hidden Markov model and N-gram models. Although these techniques perform well and lead to efficient systems, they approach their maximum…

The hidden Markov model (HMM) is a fundamental tool for sequence modeling that cleanly separates the hidden state from the emission structure. However, this separation makes it difficult to fit HMMs to large datasets in modern NLP, and they…

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…

We propose an information theoretic framework for quantitative assessment of acoustic modeling for hidden Markov model (HMM) based automatic speech recognition (ASR). Acoustic modeling yields the probabilities of HMM sub-word states for a…

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We…

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We…

Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that deal with the…

This paper is concerned with automatic continuous speech recognition using trainable systems. The aim of this work is to build acoustic models for spoken Swedish. This is done employing hidden Markov models and using the SpeechDat database…

Hidden Markov Model (HMM) is often regarded as the dynamical model of choice in many fields and applications. It is also at the heart of most state-of-the-art speech recognition systems since the 70's. However, from Gaussian mixture models…

This paper introduces a set of acoustic modeling techniques for utterance verification (UV) based continuous speech recognition (CSR). Utterance verification in this work implies the ability to determine when portions of a hypothesized word…

Hidden Markov models (HMMs) and conditional random fields (CRFs) are two popular techniques for modeling sequential data. Inference algorithms designed over CRFs and HMMs allow estimation of the state sequence given the observations. In…

Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to…

Nowadays, neural network models achieve state-of-the-art results in many areas as computer vision or speech processing. For sequential data, especially for Natural Language Processing (NLP) tasks, Recurrent Neural Networks (RNNs) and their…

Systems based on automatic speech recognition (ASR) technology can provide important functionality in computer assisted language learning applications. This is a young but growing area of research motivated by the large number of students…

Hidden Markov models can describe time series arising in various fields of science, by treating the data as noisy measurements of an arbitrarily complex Markov process. Sequential Monte Carlo (SMC) methods have become standard tools to…

Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based…

The field of spoken language processing is undergoing a shift from training custom-built, task-specific models toward using and optimizing spoken language models (SLMs) which act as universal speech processing systems. This trend is similar…

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…