Man-Machine Speech Communication
14th National Conference, NCMMSC 2017, Lianyungang, China, October 11–13, 2017, Revised Selected Papers
Page
%P
-
Chapter
A One-class Model for Voice Replay Attack Detection
Replay attack poses a serious security concern for automatic speaker verification systems. Most of the existing replay detection methods cast the task to a binary classification problem. In this article, by an...
-
Book and Conference Proceedings
-
Book
-
Chapter
Conclusions and Future Work
This book presents an overview of speaker recognition technology with an emphasis on how to deal with the robustness issues. Firstly, we give an introduction of speaker recognition, including its basic concept...
-
Chapter
Speaker Recognition: Introduction
In the ancient war times, officers and soldiers could recognize one friend or foe through the predetermined password(s). In real life, we human are able to get in and out of a house using keys or e-cards. Whil...
-
Chapter
Speaker-Related Robustness Issues
Speaker dependent factors, such as gender, physical condition (cold or laryngitis), speaking style (emotion state, speech rate, etc.), cross-language, accent and session variations, are major concerns in speec...
-
Chapter
Environment-Related Robustness Issues
In practical applications, many environment-related factors may influence the performance of speaker recognition. There is often no prior knowledge of these factors in advance, which makes the environment-rela...
-
Chapter
Application-Oriented Robustness Issues
With the development of speaker recognition technologies, they have been used in wide application areas. The main applications of speaker recognition technologies include the followings.
-
Article
Probabilistic Belief Embedding for Large-Scale Knowledge Population
To populate knowledge repositories, such as WordNet, Freebase and NELL, two branches of research have grown separately for decades. On the one hand, corpus-based methods which leverage unstructured free texts ...
-
Article
Open AccessNoisy training for deep neural networks in speech recognition
Deep neural networks (DNNs) have gained remarkable success in speech recognition, partially attributed to the flexibility of DNN models in learning complex patterns of speech signals. This flexibility, however...
-
Article
Statistical word sense aware topic models
LDA has been proved effective in modeling the semantic relation between surface words. This semantic information in the document collection is useful to measure the topic distribution for a document. In genera...
-
Chapter and Conference Paper
Topic Models Incorporating Statistical Word Senses
LDA considers a surface word to be identical across all documents and measures the contribution of a surface word to each topic. However, a surface word may present different signatures in different contexts, ...
-
Chapter and Conference Paper
Mining the Personal Interests of Microbloggers via Exploiting Wikipedia Knowledge
This paper focuses on an emerging research topic about mining microbloggers’ personalized interest tags from their own microblogs ever posted. It based on an intuition that microblogs indicate the daily intere...
-
Chapter and Conference Paper
Ranking Search Intents Underlying a Query
Observation on query log of search engine indicates that queries are usually ambiguous. Similar to document ranking, search intents should be ranked to facilitate information search. Previous work attempts to ...
-
Chapter and Conference Paper
Job Information Retrieval Based on Document Similarity
Job information retrieval (IR) exhibits unique characteristics compared to common IR task. First, searching precision on job posting full text is low because job descriptions cannot be properly used in common ...
-
Chapter and Conference Paper
CCC Speaker Recognition Evaluation 2006: Overview, Methods, Data, Results and Perspective
For the special session on speaker recognition of the 5th International Symposium on Chinese Spoken Language Processing (ISCSLP 2006), the Chinese Corpus Consortium (CCC), the session organizer, developed a speak...
-
Chapter and Conference Paper
UBM Based Speaker Segmentation and Clustering for 2-Speaker Detection
In this paper, a speaker segmentation method based on log-likelihood ratio score (LLRS) over universal background model (UBM) and a speaker clustering method based on difference of log-likelihood scores betwee...
-
Chapter and Conference Paper
Pitch Mean Based Frequency War**
In this paper, a novel pitch mean based frequency war** (PMFW) method is proposed to reduce the pitch variability in speech signals at the front-end of speech recognition. The warp factors used in this proce...
-
Article
A Dialectal Chinese Speech Recognition Framework
A framework for dialectal Chinese speech recognition is proposed and studied, in which a relatively small dialectal Chinese (or in other words Chinese influenced by the native dialect) speech corpus and dialec...
-
Chapter and Conference Paper
State-Dependent Phoneme-Based Model Merging for Dialectal Chinese Speech Recognition
Aiming at building a dialectal Chinese speech recognizer from a standard Chinese speech recognizer with a small amount of dialectal Chinese speech, a novel, simple but effective acoustic modeling method, named st...
