
Contents
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
33.1 Introduction 33.1 Introduction
-
33.2 Acoustic Parameterization and Modelling 33.2 Acoustic Parameterization and Modelling
-
33.2.1 Acoustic Feature Analysis 33.2.1 Acoustic Feature Analysis
-
33.2.2 Acoustic Models 33.2.2 Acoustic Models
-
33.2.3 Adaptation 33.2.3 Adaptation
-
33.2.4 Deep Neural Networks 33.2.4 Deep Neural Networks
-
-
33.3 Lexical and Pronunciation Modelling 33.3 Lexical and Pronunciation Modelling
-
33.4 Language Modelling 33.4 Language Modelling
-
33.5 Decoding 33.5 Decoding
-
33.6 State-of-the-Art Performance 33.6 State-of-the-Art Performance
-
33.7 Discussion and Perspectives 33.7 Discussion and Perspectives
-
Further Reading and Relevant Resources Further Reading and Relevant Resources
-
References References
-
-
-
-
-
-
-
-
33 Speech Recognition
Get accessLori Lamel is a Senior Research Scientist at LIMSI CNRS, which she joined as a permanent researcher in October 1991. She holds a PhD degree in EECS from MIT, and an HDR in CS from the University of Paris XI. She also has over 330 peer-reviewed publications. Her research covers a range of topics in the field of spoken language processing and corpus-based linguistics. She is a Fellow of ISCA and IEEE and serves on the ISCA board.
Jean-Luc Gauvain is a Senior Research Scientist at the CNRS and Spoken Language Processing Group Head at LISN. He received a doctorate in electronics and a computer science HDR degree from Paris-Sud University. His research centres on speech technologies, including speech recognition, audio indexing, and language and speaker recognition. He has contributed over 300 publications to this field and was awarded a CNRS silver medal in 2007. He served as co-editor-in-chief for Speech Communication Journal in 2006–2008, and as scientific coordinator for the Quaero research programme in 2008–2013. He is an ISCA Fellow.
-
Published:10 December 2015
Cite
Abstract
Speech recognition is concerned with converting the speech waveform, an acoustic signal, into a sequence of words. Today’s best-performing approaches are based on a statistical modelization of the speech signal. This chapter provides an overview of the main topics addressed in speech recognition: that is, acoustic-phonetic modelling, lexical representation, language modelling, decoding, and model adaptation. The focus is on methods used in state-of-the-art, speaker-independent, large-vocabulary continuous speech recognition (LVCSR). Some of the technology advances over the last decade are highlighted. Primary application areas for such technology initially addressed dictation tasks and interactive systems for limited domain information access (usually referred to as spoken language dialogue systems). The last decade has witnessed a wider coverage of languages, as well as growing interest in transcription systems for information archival and retrieval, media monitoring, automatic subtitling and speech analytics. Some outstanding issues and directions of future research are discussed.
Sign in
Personal account
- Sign in with email/username & password
- Get email alerts
- Save searches
- Purchase content
- Activate your purchase/trial code
- Add your ORCID iD
Purchase
Our books are available by subscription or purchase to libraries and institutions.
Purchasing informationMonth: | Total Views: |
---|---|
October 2022 | 12 |
November 2022 | 8 |
December 2022 | 7 |
January 2023 | 12 |
February 2023 | 4 |
March 2023 | 9 |
April 2023 | 8 |
May 2023 | 3 |
June 2023 | 8 |
July 2023 | 4 |
August 2023 | 10 |
September 2023 | 2 |
October 2023 | 8 |
November 2023 | 4 |
January 2024 | 2 |
February 2024 | 4 |
March 2024 | 15 |
April 2024 | 2 |
May 2024 | 10 |
June 2024 | 8 |
July 2024 | 6 |
August 2024 | 8 |
September 2024 | 16 |
October 2024 | 8 |
November 2024 | 3 |
December 2024 | 8 |
January 2025 | 6 |
February 2025 | 2 |
March 2025 | 10 |
April 2025 | 7 |
Get help with access
Institutional access
Access to content on Oxford Academic is often provided through institutional subscriptions and purchases. If you are a member of an institution with an active account, you may be able to access content in one of the following ways:
IP based access
Typically, access is provided across an institutional network to a range of IP addresses. This authentication occurs automatically, and it is not possible to sign out of an IP authenticated account.
Sign in through your institution
Choose this option to get remote access when outside your institution. Shibboleth/Open Athens technology is used to provide single sign-on between your institution’s website and Oxford Academic.
If your institution is not listed or you cannot sign in to your institution’s website, please contact your librarian or administrator.
Sign in with a library card
Enter your library card number to sign in. If you cannot sign in, please contact your librarian.
Society Members
Society member access to a journal is achieved in one of the following ways:
Sign in through society site
Many societies offer single sign-on between the society website and Oxford Academic. If you see ‘Sign in through society site’ in the sign in pane within a journal:
If you do not have a society account or have forgotten your username or password, please contact your society.
Sign in using a personal account
Some societies use Oxford Academic personal accounts to provide access to their members. See below.
Personal account
A personal account can be used to get email alerts, save searches, purchase content, and activate subscriptions.
Some societies use Oxford Academic personal accounts to provide access to their members.
Viewing your signed in accounts
Click the account icon in the top right to:
Signed in but can't access content
Oxford Academic is home to a wide variety of products. The institutional subscription may not cover the content that you are trying to access. If you believe you should have access to that content, please contact your librarian.
Institutional account management
For librarians and administrators, your personal account also provides access to institutional account management. Here you will find options to view and activate subscriptions, manage institutional settings and access options, access usage statistics, and more.