DE eng

Search in the Catalogues and Directories

Hits 1 – 20 of 20

1
Non-Parametric Bayesian Subspace Models for Acoustic Unit Discovery
In: https://hal.archives-ouvertes.fr/hal-03467205 ; 2021 (2021)
Abstract: This work investigates subspace non-parametric models for the task of learning a set of acoustic units from unlabeled speech recordings. We constrain the base-measure of a Dirichlet-Process mixture with a phonetic subspace-estimated from other source languages-to build an educated prior, thereby forcing the learned acoustic units to resemble phones of known source languages. Two types of models are proposed: (i) the Subspace HMM (SHMM) which assumes that the phonetic subspace is the same for every language, (ii) the Hierarchical-Subspace HMM (H-SHMM) which relaxes this assumption and allows to have a language-specific subspace estimated on the unlabeled target data. These models are applied on 3 languages: English, Yoruba and Mboshi and they are compared with various competitive acoustic units discovery baselines. Experimental results show that both subspace models outperform other systems in terms of clustering quality and segmentation accuracy. Moreover, we observe that the H-SHMM provides results superior to the SHMM supporting the idea that language-specific priors are preferable to language-agnostic priors for acoustic unit discovery.
Keyword: [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD]
URL: https://hal.archives-ouvertes.fr/hal-03467205/document
https://hal.archives-ouvertes.fr/hal-03467205/file/NONPARAMETRIC_BAYESIAN_SUBSPACE_MODELS_AUD-final%20%281%29.pdf
https://hal.archives-ouvertes.fr/hal-03467205
BASE
Hide details
2
Morpho-syntactically annotated corpora provided for the PARSEME Shared Task on Semi-Supervised Identification of Verbal Multiword Expressions (edition 1.2)
BASE
Show details
3
A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery ...
BASE
Show details
4
Turkish Natural Language Processing
Oflazer, Kemal [Herausgeber]; Saraçlar, Murat [Herausgeber]. - Cham : Springer International Publishing, 2018
DNB Subject Category Language
Show details
5
Score Normalization for Keyword Search
BASE
Show details
6
Classification and ranking approaches to discriminative language modeling for ASR
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 21 (2013) 2, 291-300
OLC Linguistik
Show details
7
Discriminative language modeling with linguistic and statistically derived features
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 20 (2012) 2, 540-550
BLLDB
OLC Linguistik
Show details
8
Performance analysis and improvement of Turkish broadcast news retrieval
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 20 (2012) 3, 731-741
BLLDB
OLC Linguistik
Show details
9
Lexical-phonetic automata for spoken utterance indexing and retrieval
In: International Conference on Speech Communication and Technologies ; https://hal.archives-ouvertes.fr/hal-00757765 ; International Conference on Speech Communication and Technologies, Sep 2012, Portland, United States (2012)
BASE
Show details
10
Turkish Broadcast News Speech and Transcripts
Saraçlar, Murat. - : Linguistic Data Consortium, 2012. : https://www.ldc.upenn.edu, 2012
BASE
Show details
11
Turkish Broadcast News Speech and Transcripts ...
Saraçlar, Murat. - : Linguistic Data Consortium, 2012
BASE
Show details
12
Lattice indexing for spoken term detection
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 19 (2011) 8, 2338-2347
BLLDB
OLC Linguistik
Show details
13
Lattice extension and vocabulary adaptation for Turkish LVCSR
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 17 (2009) 1, 163-173
BLLDB
OLC Linguistik
Show details
14
Turkish broadcast news transcription and retrieval
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 17 (2009) 5, 874-883
BLLDB
OLC Linguistik
Show details
15
Discriminative n-gram language modeling
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 21 (2007) 2, 373-392
BLLDB
OLC Linguistik
Show details
16
Utterance classification with discriminative language modeling
In: Speech communication. - Amsterdam [u.a.] : Elsevier 48 (2006) 3-4, 276-287
BLLDB
OLC Linguistik
Show details
17
Pronunciation change in conversational speech and its implications for automatic speech recognition
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 18 (2004) 4, 375-395
BLLDB
Show details
18
Pronunciation change in conversational speech and its implications for automatic speech recognition
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 18 (2004) 4, 375-396
OLC Linguistik
Show details
19
Pronunciation modeling by sharing Gaussian densities across phonetic models
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 14 (2000) 2, 137-160
BLLDB
Show details
20
Modeling pronunciation variation for automatic speech recognition
Strik, Helmer (Hrsg.); Adda-Decker, Martine (Mitarb.); Lamel, Lori (Mitarb.)...
In: Speech communication. - Amsterdam [u.a.] : Elsevier 29 (1999) 2-4, 81-246
BLLDB
Show details

Catalogues
0
0
9
0
1
0
0
Bibliographies
10
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
7
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern