Open AccessProceedings Article
A Generative Modeling Framework for Structured Hidden Speech Dynamics
Reads0
Chats0
TLDR
A structured speech model is outlined, equipped with long-contextual-span capabilities that are missing in the HMM approach, and the pros and cons of the structured generative modeling approach in comparison with the structured discriminative classification approach are discussed.Citations
More filters
Journal ArticleDOI
Discriminative learning in sequential pattern recognition
Xiaodong He,Li Deng,Wu Chou +2 more
TL;DR: The main goal of this article is to provide an underlying foundation for MMI, MCE, and MPE/MWE at the objective function level to facilitate the development of new parameter optimization techniques and to incorporate other pattern recognition concepts, e.g., discriminative margins [66], into the current discrim inative learning paradigm.
Book ChapterDOI
Phoneme Recognition on the TIMIT Database
Carla Lopes,Fernando Perdigão +1 more
TL;DR: Speech recognition based on phones is very attractive since it is inherently free from vocabulary limitations, but large Vocabulary ASR systems’ performance depends on the quality of the phone recognizer, so research teams continue developing phone recognizers, in order to enhance their performance as much as possible.
Book
Discriminative learning for speech recognition
Xiaodong He,Li Deng +1 more
TL;DR: This book introduces the background and mainstream methods of probabilistic modeling and discriminative parameter optimization for speech recognition and includes technical details on the derivation of the parameter optimization formulas for exponential-family distribut ons, discrete hidden Markov models (HMMs), and continuous-density HMMs in discriminating learning.
Posted Content
Phoneme recognition in TIMIT with BLSTM-CTC
TL;DR: The performance of a recurrent neural network is compared with the best results published so far on phoneme recognition in the TIMIT database and a single recurrent network is applied to the same task.
Patent
Minimum classification error training with growth transformation optimization
Xiaodong He,Li Deng +1 more
TL;DR: In this paper, the hidden Markov model (HMM) parameters are updated using update equations based on growth transformation optimization of a minimum classification error objective function using the list of N-best word sequences obtained by decoding the training data with the current-iteration HMM parameters.
References
More filters
Book
Fundamentals of speech recognition
TL;DR: This book presents a meta-modelling framework for speech recognition that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of manually modeling speech.
Journal ArticleDOI
From HMM's to segment models: a unified view of stochastic modeling for speech recognition
TL;DR: A general stochastic model is described that encompasses most of the models proposed in the literature for speech recognition, pointing out similarities in terms of correlation and parameter tying assumptions, and drawing analogies between segment models and HMMs.
Proceedings ArticleDOI
Hidden conditional random fields for phone classification.
TL;DR: This paper presents the results on the TIMIT phone classification task and shows that HCRFs outperforms comparable ML and CML/MMI trained HMMs and has the ability to handle complex features without any change in training procedure.
Journal ArticleDOI
Structured language modeling
Ciprian Chelba,Frederick Jelinek +1 more
TL;DR: An attempt at using the syntactic structure in natural language for improved language models for speech recognition using an original probabilistic parameterization of a shift-reduce parser.
Journal ArticleDOI
A probabilistic framework for segment-based speech recognition
TL;DR: This work examines a maximum a posteriori decoding strategy for feature-based recognizers and develops a normalization criterion useful for a segment-based speech recognizer.