English
Related papers

Related papers: Context-Dependent Acoustic Modeling without Explic…

200 papers

Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic…

Computation and Language · Computer Science 2019-07-11 Wei-Ning Hsu , David Harwath , James Glass

Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCFGs) are widely used structured models, both of which can be represented as factor graph grammars (FGGs), a powerful formalism capable of describing a wide range of…

Computation and Language · Computer Science 2022-05-03 Songlin Yang , Wei Liu , Kewei Tu

In recent years, deep-learning-based speech emotion recognition models have outperformed classical machine learning models. Previously, neural network designs, such as Multitask Learning, have accounted for variations in emotional…

Machine Learning · Computer Science 2021-09-10 Lance Ying , Amrit Romana , Emily Mower Provost

In the field of text-independent speaker recognition, dynamic models that adapt along the time axis have been proposed to consider the phoneme-varying characteristics of speech. However, a detailed analysis of how dynamic models work…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-09 Seong-Hu Kim , Hyeonuk Nam , Yong-Hwa Park

Deep learning sequence models have led to a marked increase in performance for a range of Natural Language Processing tasks, but it remains an open question whether they are able to induce proper hierarchical generalizations for…

Computation and Language · Computer Science 2019-06-11 Ethan Wilcox , Roger Levy , Richard Futrell

(Part of the abstract) In this thesis, we investigate the use of unsupervised spoken term discovery in tackling this problem. Unsupervised spoken term discovery aims to discover topic-related terminologies in a speech without knowing the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-01 Man-Ling Sung

We present a deep neural network (DNN) acoustic model that includes parametrised and differentiable pooling operators. Unsupervised acoustic model adaptation is cast as the problem of updating the decision boundaries implemented by each…

Computation and Language · Computer Science 2016-07-14 Pawel Swietojanski , Steve Renals

In the human ear, the basilar membrane plays a central role in sound recognition. When excited by sound, this membrane responds with a frequency-dependent displacement pattern that is detected and identified by the auditory hair cells…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-10 Woo Seok Lee , Hyunjae Kim , Andrew N. Cleland , Kang-Hun Ahn

This study presents a hybrid deep learning architecture that integrates LSTM, CNN, and an Attention mechanism to enhance the classification of web content based on text. Pretrained GloVe embeddings are used to represent words as dense…

Computation and Language · Computer Science 2025-12-29 Mykola Kuz , Ihor Lazarovych , Mykola Kozlenko , Mykola Pikuliak , Andrii Kvasniuk

While discrete latent variable models have had great success in self-supervised learning, most models assume that frames are independent. Due to the segmental nature of phonemes in speech perception, modeling dependencies among latent…

Computation and Language · Computer Science 2022-11-01 Sung-Lin Yeh , Hao Tang

Speech perception involves storing and integrating sequentially presented items. Recent work in cognitive neuroscience has identified temporal and contextual characteristics in humans' neural encoding of speech that may facilitate this…

Computation and Language · Computer Science 2024-05-15 Oli Danyi Liu , Hao Tang , Naomi Feldman , Sharon Goldwater

Automatic feature extraction using neural networks has accomplished remarkable success for images, but for sound recognition, these models are usually modified to fit the nature of the multi-dimensional temporal representation of the audio…

Machine Learning · Computer Science 2019-04-30 Fady Medhat , David Chesmore , John Robinson

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…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-26 Giampiero Salvi

Google's multilingual speech recognition system combines low-level acoustic signals with language-specific recognizer signals to better predict the language of an utterance. This paper presents our experience with different signal…

Machine Learning · Computer Science 2019-11-05 Shengye Wang , Li Wan , Yang Yu , Ignacio Lopez Moreno

Automated speech recognition coverage of the world's languages continues to expand. However, standard phoneme based systems require handcrafted lexicons that are difficult and expensive to obtain. To address this problem, we propose a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-17 Arindrima Datta , Guanlong Zhao , Bhuvana Ramabhadran , Eugene Weinstein

Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-19 David M. Chan , Shalini Ghosh , Debmalya Chakrabarty , Björn Hoffmeister

Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more…

Computation and Language · Computer Science 2019-11-21 Parnia Bahar , Albert Zeyer , Ralf Schlüter , Hermann Ney

Several studies have been conducted to automatically recognize activities of construction equipment using their generated sound patterns. Most of these studies are focused on single-machine scenarios under controlled environments. However,…

Signal Processing · Electrical Eng. & Systems 2020-04-28 Behnam Sherafat , Abbas Rashidi , Siyuan Song

In recent years, the standard hybrid DNN-HMM speech recognizers are outperformed by the end-to-end speech recognition systems. One of the very promising approaches is the grapheme Wav2Vec 2.0 model, which uses the self-supervised…

Computation and Language · Computer Science 2022-10-24 Jan Švec , Jan Lehečka , Luboš Šmídl

Videos are inherently multimodal. This paper studies the problem of how to fully exploit the abundant multimodal clues for improved video categorization. We introduce a hybrid deep learning framework that integrates useful clues from…

Multimedia · Computer Science 2017-06-15 Yu-Gang Jiang , Zuxuan Wu , Jinhui Tang , Zechao Li , Xiangyang Xue , Shih-Fu Chang