Linear spectral transformation for robust speech recognition using maximum mutual information

Donghyun Kim; Dongsuk Yook

doi:10.1109/LSP.2006.891337

Linear spectral transformation for robust speech recognition using maximum mutual information

Donghyun Kim, Dongsuk Yook

Research output: Contribution to journal › Article › peer-review

14 Citations (Scopus)

Abstract

This paper presents a transformation-based rapid adaptation technique for robust speech recognition using a linear spectral transformation (LST) and a maximum mutual information (MMI) criterion. Previously, a maximum likelihood linear spectral transformation (ML-LST) algorithm was proposed for fast adaptation in unknown environments. Since the MMI estimation method does not require evenly distributed training data and increases the a posteriori probability of the word sequences of the training data, we combine the linear spectral transformation method and the MMI estimation technique in order to achieve extremely rapid adaptation using only one word of adaptation data. The proposed algorithm, called MMI-LST, was implemented using the extended Baum-Welch algorithm and phonetic lattices, and evaluated on the TIMIT and FFMTIMIT corpora. It provides a relative reducion in the speech recognition error rate of 11.1% using only 0.25 s of adaptation data.

Original language	English
Pages (from-to)	496-499
Number of pages	4
Journal	IEEE Signal Processing Letters
Volume	14
Issue number	7
DOIs	https://doi.org/10.1109/LSP.2006.891337
Publication status	Published - 2007 Jul

Bibliographical note

Funding Information:
Manuscript received August 1, 2006; revised November 1, 2006. This work was supported by Grant R01-2006-000-11162-0 from the Basic Research Program of the Korea Science and Engineering Foundation. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Steve Renals.

Keywords

Linear spectral transformation
Maximum mutual information (MMI)
Rapid adaptation
Robust speech recognition

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1109/LSP.2006.891337

Cite this

@article{cca37a5157e646da8c79db987c7ac0b0,

title = "Linear spectral transformation for robust speech recognition using maximum mutual information",

abstract = "This paper presents a transformation-based rapid adaptation technique for robust speech recognition using a linear spectral transformation (LST) and a maximum mutual information (MMI) criterion. Previously, a maximum likelihood linear spectral transformation (ML-LST) algorithm was proposed for fast adaptation in unknown environments. Since the MMI estimation method does not require evenly distributed training data and increases the a posteriori probability of the word sequences of the training data, we combine the linear spectral transformation method and the MMI estimation technique in order to achieve extremely rapid adaptation using only one word of adaptation data. The proposed algorithm, called MMI-LST, was implemented using the extended Baum-Welch algorithm and phonetic lattices, and evaluated on the TIMIT and FFMTIMIT corpora. It provides a relative reducion in the speech recognition error rate of 11.1% using only 0.25 s of adaptation data.",

keywords = "Linear spectral transformation, Maximum mutual information (MMI), Rapid adaptation, Robust speech recognition",

author = "Donghyun Kim and Dongsuk Yook",

note = "Funding Information: Manuscript received August 1, 2006; revised November 1, 2006. This work was supported by Grant R01-2006-000-11162-0 from the Basic Research Program of the Korea Science and Engineering Foundation. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Steve Renals.",

year = "2007",

month = jul,

doi = "10.1109/LSP.2006.891337",

language = "English",

volume = "14",

pages = "496--499",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "7",

}

TY - JOUR

T1 - Linear spectral transformation for robust speech recognition using maximum mutual information

AU - Kim, Donghyun

AU - Yook, Dongsuk

N1 - Funding Information: Manuscript received August 1, 2006; revised November 1, 2006. This work was supported by Grant R01-2006-000-11162-0 from the Basic Research Program of the Korea Science and Engineering Foundation. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Steve Renals.

PY - 2007/7

Y1 - 2007/7

N2 - This paper presents a transformation-based rapid adaptation technique for robust speech recognition using a linear spectral transformation (LST) and a maximum mutual information (MMI) criterion. Previously, a maximum likelihood linear spectral transformation (ML-LST) algorithm was proposed for fast adaptation in unknown environments. Since the MMI estimation method does not require evenly distributed training data and increases the a posteriori probability of the word sequences of the training data, we combine the linear spectral transformation method and the MMI estimation technique in order to achieve extremely rapid adaptation using only one word of adaptation data. The proposed algorithm, called MMI-LST, was implemented using the extended Baum-Welch algorithm and phonetic lattices, and evaluated on the TIMIT and FFMTIMIT corpora. It provides a relative reducion in the speech recognition error rate of 11.1% using only 0.25 s of adaptation data.

AB - This paper presents a transformation-based rapid adaptation technique for robust speech recognition using a linear spectral transformation (LST) and a maximum mutual information (MMI) criterion. Previously, a maximum likelihood linear spectral transformation (ML-LST) algorithm was proposed for fast adaptation in unknown environments. Since the MMI estimation method does not require evenly distributed training data and increases the a posteriori probability of the word sequences of the training data, we combine the linear spectral transformation method and the MMI estimation technique in order to achieve extremely rapid adaptation using only one word of adaptation data. The proposed algorithm, called MMI-LST, was implemented using the extended Baum-Welch algorithm and phonetic lattices, and evaluated on the TIMIT and FFMTIMIT corpora. It provides a relative reducion in the speech recognition error rate of 11.1% using only 0.25 s of adaptation data.

KW - Linear spectral transformation

KW - Maximum mutual information (MMI)

KW - Rapid adaptation

KW - Robust speech recognition

UR - http://www.scopus.com/inward/record.url?scp=34347395939&partnerID=8YFLogxK

U2 - 10.1109/LSP.2006.891337

DO - 10.1109/LSP.2006.891337

M3 - Article

AN - SCOPUS:34347395939

SN - 1070-9908

VL - 14

SP - 496

EP - 499

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 7

ER -

Linear spectral transformation for robust speech recognition using maximum mutual information

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this