GB2336015A - Speech analysis system - Google Patents

Speech analysis system

Info

Publication number
GB2336015A
GB2336015A GB9917606A GB9917606A GB2336015A GB 2336015 A GB2336015 A GB 2336015A GB 9917606 A GB9917606 A GB 9917606A GB 9917606 A GB9917606 A GB 9917606A GB 2336015 A GB2336015 A GB 2336015A
Authority
GB
United Kingdom
Prior art keywords
distortion
data vector
vectors
speech
estimate
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
GB9917606A
Other versions
GB9917606D0 (en
GB2336015B (en
Inventor
Robert William Series
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
UK Secretary of State for Defence
Original Assignee
UK Secretary of State for Defence
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from GBGB9706174.1A external-priority patent/GB9706174D0/en
Application filed by UK Secretary of State for Defence filed Critical UK Secretary of State for Defence
Priority to GB9917606A priority Critical patent/GB2336015B/en
Priority claimed from PCT/GB1998/000615 external-priority patent/WO1998043238A1/en
Publication of GB9917606D0 publication Critical patent/GB9917606D0/en
Publication of GB2336015A publication Critical patent/GB2336015A/en
Application granted granted Critical
Publication of GB2336015B publication Critical patent/GB2336015B/en
Anticipated expiration legal-status Critical
Revoked legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/065—Adaptation
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
    • G10L15/142—Hidden Markov Models [HMMs]

Abstract

A speech analysis system (10) incorporates a filterbank analyser (18) producing successive frequency data vectors for a speech signal from two speakers. From each data vector, units (22A and 22B) produce a set of modified data vectors compensated for differing forms of distortion associated with respective speakers. A computer (24) matches modified data vectors to hidden Markov model states. It identifies the modified data vector in each set exhibiting greatest matching probability, the model state matched therewith, the form of distortion with which it is associated and the model class, i.e. speech or noise. The matched model state has a mean value providing an estimate of its associated data vector. The estimate is compared with its associated data vector, and their difference is averaged with others associated with a like form of distortion in an infinite response filter bank (48A or 48B) to provide compensation for that form of distortion. Averaged difference vectors provide compensation for multiple forms of distortion associated with respective speakers.
GB9917606A 1997-03-25 1998-02-26 Speech analysis system Revoked GB2336015B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
GB9917606A GB2336015B (en) 1997-03-25 1998-02-26 Speech analysis system

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
GBGB9706174.1A GB9706174D0 (en) 1997-03-25 1997-03-25 Recognition system
GBGB9714345.7A GB9714345D0 (en) 1997-03-25 1997-07-09 Speech analysis system
GB9917606A GB2336015B (en) 1997-03-25 1998-02-26 Speech analysis system
PCT/GB1998/000615 WO1998043238A1 (en) 1997-03-25 1998-02-26 Speech analysis system

Publications (3)

Publication Number Publication Date
GB9917606D0 GB9917606D0 (en) 1999-09-29
GB2336015A true GB2336015A (en) 1999-10-06
GB2336015B GB2336015B (en) 2001-01-31

Family

ID=27268789

Family Applications (1)

Application Number Title Priority Date Filing Date
GB9917606A Revoked GB2336015B (en) 1997-03-25 1998-02-26 Speech analysis system

Country Status (1)

Country Link
GB (1) GB2336015B (en)

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Gu Yong et al, Proceedings of EUROSPEECH, Paris, 26-28 Sept 1989, vol. 1, conf. 1, pages 258-261 *
Y Zhao, Proceedings of ICASSP, Detroit, 9-12 May 1995, vol. 1, pages 712-715 *
Y Zhao, Speech Communication, vol. 18, no. 1, January 1996, pages 65-77 *

Also Published As

Publication number Publication date
GB9917606D0 (en) 1999-09-29
GB2336015B (en) 2001-01-31

Similar Documents

Publication Publication Date Title
Qi et al. Voiced-unvoiced-silence classifications of speech using hybrid features and a network classifier
Thomas et al. Recognition of reverberant speech using frequency domain linear prediction
GB2248513B (en) Methods and apparatus for verifying the originator of a sequence of operations
Liu et al. Audio-visual continuous speech recognition using a coupled hidden Markov model.
Ozerov et al. Uncertainty-based learning of acoustic models from noisy data
Ali et al. Robust auditory-based speech processing using the average localized synchrony detection
CA2192397A1 (en) Method and system for performing speech recognition
Takiguchi et al. PCA-Based Speech Enhancement for Distorted Speech Recognition.
Choi et al. Multichannel signal separation for cocktail party speech recognition: A dynamic recurrent network
Sinith et al. Raga recognition using fibonacci series based pitch distribution in Indian Classical Music
de-La-Calle-Silos et al. Synchrony-based feature extraction for robust automatic speech recognition
TW355233B (en) Method and recognizer for recognizing tonal acoustic sound signals
Damper et al. Improving speaker identification in noise by subband processing and decision fusion
GB2336015A (en) Speech analysis system
Stouten et al. Robust speech recognition using model-based feature enhancement
TW374152B (en) Voice analysis system
Khosravy et al. Harmonic adaptive speech synthesis
Binh et al. A high-performance speech-recognition method based on a nonlinear neural network
Akula et al. Speaker identification in room reverberation using GMM-UBM
Oh et al. Preprocessing of independent vector analysis using feed-forward network for robust speech recognition
Xian et al. Monaural speech enhancement based on two stage long short-term memory networks
Stern Robust speech recognition
Murai et al. Agglomerative Hierarchical Clustering of Basis Vector for Monaural Sound Source Separation Based on NMF
Tsurufuji et al. A voice activated car audio system
Kim et al. Filtering on hidden Markov models

Legal Events

Date Code Title Description
732E Amendments to the register in respect of changes of name or changes affecting rights (sect. 32/1977)
732E Amendments to the register in respect of changes of name or changes affecting rights (sect. 32/1977)
773K Patent revoked under sect. 73(2)/1977