Home Catalogue search

eng

Refine your search:

Search in the Catalogues and Directories






	Sort by
Simple Search

Page: 1 2

Hits 1 – 20 of 27

1	Parallel Reference Speaker Weighting for Kinematic-Independent Acoustic-to-Articulatory Inversion
	Ji, An; Johnson, Michael T.; Berry, Jeffrey J.
	In: Speech Pathology and Audiology Faculty Research and Publications (2016)
	Abstract: Acoustic-to-articulatory inversion, the estimation of articulatory kinematics from an acoustic waveform, is a challenging but important problem. Accurate estimation of articulatory movements has the potential for significant impact on our understanding of speech production, on our capacity to assess and treat pathologies in a clinical setting, and on speech technologies such as computer aided pronunciation assessment and audio-video synthesis. However, because of the complex and speaker-specific relationship between articulation and acoustics, existing approaches for inversion do not generalize well across speakers. As acquiring speaker-specific kinematic data for training is not feasible in many practical applications, this remains an important and open problem. This paper proposes a novel approach to acoustic-to-articulatory inversion, Parallel Reference Speaker Weighting (PRSW), which requires no kinematic data for the target speaker and a small amount of acoustic adaptation data. PRSW hypothesizes that acoustic and kinematic similarities are correlated and uses speaker-adapted articulatory models derived from acoustically derived weights. The system was assessed using a 20-speaker data set of synchronous acoustic and Electromagnetic Articulography (EMA) kinematic data. Results demonstrate that by restricting the reference group to a subset consisting of speakers with strong individual speaker-dependent inversion performance, the PRSW method is able to attain kinematic-independent acoustic-to-articulatory inversion performance nearly matching that of the speaker-dependent model, with an average correlation of 0.62 versus 0.63. This indicates that given a sufficiently complete and appropriately selected reference speaker set for adaptation, it is possible to create effective articulatory models without kinematic training data.
	Keyword: acoustic-to-articulatory inversion; acoustics; adaptation models; Electrical and Computer Engineering; electromagnetic articulography; hidden markov models; kinematics; maximum likelihood estimation; speech; Speech Pathology and Audiology; speech processing
	URL: https://epublications.marquette.edu/cgi/viewcontent.cgi?article=1038&context=spaud_fac https://epublications.marquette.edu/spaud_fac/39
	BASE
	Hide details

2	Emulating DNA: Rigorous Quantification of Evidential Weight in Transparent and Testable Forensic Speaker Recognition
	Gonzalez-Rodriguez, Joaquin; Rose, Philip; Ramos, Daniel...
	In: IEEE Transactions on Audio, Speech, and Language Processing (2015)
	BASE
	Show details

3	Technical forensic speaker recognition: Evaluation, types and testing of evidence
	Rose, Philip
	In: Computer Speech and Language (2015)
	BASE
	Show details

4	Technical forensic speaker recognition: Evaluation, types and testing of evidence
	Rose, Philip
	In: Computer Speech and Language (2015)
	BASE
	Show details

5	A Fast Variational Approach for Learning Markov Random Field Language Models
	Jernite, Yacine; Rush, Alexander M; Sontag, David
	In: DTIC (2015)
	BASE
	Show details

6	Joint estimation of intersecting context tree models
	Galves, Antonio; Garivier, Aurélien; Gassiat, Elisabeth
	In: ISSN: 0303-6898 ; EISSN: 1467-9469 ; Scandinavian Journal of Statistics ; https://hal.archives-ouvertes.fr/hal-00738202 ; Scandinavian Journal of Statistics, Wiley, 2012, pp.early view (2012)
	BASE
	Show details

7	Entity relation detection with Factorial Hidden Markov Models and Maximum Entropy Discriminant Latent Dirichlet Allocations.
	Li, Dingcheng. - 2012
	BASE
	Show details

8	Improving the Capacity of Language Recognition Systems to Handle Rare Languages Using Radio Broadcast Data
	Burget, Lukas
	In: DTIC (2011)
	BASE
	Show details

9	Gibbs Sampling for the Uninitiated
	Resnik, Philip; Hardisty, Eric
	In: DTIC (2010)
	BASE
	Show details

10	Implementation and Performance Exploration of a Cross-Genre Part of Speech Tagging Methodology to Determine Dialog Act Tags in the Chat Domain
	Hitt, J. R.
	In: DTIC (2010)
	BASE
	Show details

11	Portable Language-Independent Adaptive Translation from OCR
	Natarajan, Prem
	In: DTIC (2009)
	BASE
	Show details

12	A document image model and estimation algorithm for optimized JPEG decompression
	Tak-Shing, Wong; Bouman, C. A.; Pollak, I....
	In: Department of Electrical and Computer Engineering Faculty Publications (2009)
	BASE
	Show details

13	CSIR at TREC 2008 Expert Search Task: Modeling Expert Evidence in Expert Search
	Jiang, Jiepu; Lu, Wei; Zhao, Haozhen
	In: DTIC (2008)
	BASE
	Show details

14	Investigation on Mandarin Broadcast News Speech Recognition
	Hwang, Mei-Yuh; Lei, Xin; Wang, Wen...
	In: DTIC (2006)
	BASE
	Show details

15	PROxy Based Estimation (PROBE) for SQL
	Schoedel, Rob
	In: DTIC (2006)
	BASE
	Show details

16	Minimum Bayes-Risk Decoding for Statistical Machine Translation
	Kumar, Shankar; Byrne, William
	In: DTIC (2004)
	BASE
	Show details

17	Blind Beamforming for Collaborative Array Processing in Sensor Networks
	Yao, Kung
	In: DTIC AND NTIS (2004)
	BASE
	Show details

18	Localized Smoothing for Multinomial Language Models
	Lavrenko, Victor
	In: DTIC (2000)
	BASE
	Show details

19	Algorithms That Learn to Extract Information BBN: Description of the Sift System as Used for MUC-7
	Miller, Scott; Crystal, Michael; Fox, Heidi...
	In: DTIC (1998)
	BASE
	Show details

20	Scalable Trigram Backoff Language Models
	Seymore, Kristie; Rosenfeld, Ronald
	In: DTIC AND NTIS (1996)
	BASE
	Show details

Page: 1 2

© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern