Enhanced speech recognition using an articulatory production model trained on X-ray data

Blackburn, C. Simon; Young, Steve

doi:10.1006/csla.2001.0165

Cited by 3 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One is to better understand how speech is perceived and produced by humans ͑e.g., Rubin, Baer, and Mermelstein, 1981͒, and the other is to develop articulatory-based techniques for automatic speech recognition ͑e.g., Blackburn and Young, 2000a͒ and speech synthesis ͑e.g., Greenwood, Goodyear, and Martin, 1992͒. In the service of these purposes, computational models have been developed to simulate the forward mapping from articulation to acoustics ͑e.g., Baer et al, 1991;Beautemps, Badin, and Laboissiere, 1995͒. These forward models have been based upon articulatory and acoustic dimensions that are known to convey phonetic information, and upon physical principles of the vocal tract.…”

Section: Introductionmentioning

confidence: 99%

“…Most forward models developed thus far can be thought of as theory-driven because they are, in large part, derived from physical principles of the vocal tract ͑for an exception in automatic speech recognition, see Blackburn and Young, 2000a͒. These theory-driven models have served as valuable research tools for relating the underlying theories to empirical data on speech production.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A neural network model of the articulatory-acoustic forward mapping trained on recordings of articulatory parameters

Kello

Plaut

2004

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Three neural network models were trained on the forward mapping from articulatory positions to acoustic outputs for a single speaker of the Edinburgh multi-channel articulatory speech database. The model parameters (i.e., connection weights) were learned via the backpropagation of error signals generated by the difference between acoustic outputs of the models, and their acoustic targets. Efficacy of the trained models was assessed by subjecting the models' acoustic outputs to speech intelligibility tests. The results of these tests showed that enough phonetic information was captured by the models to support rates of word identification as high as 84%, approaching an identification rate of 92% for the actual target stimuli. These forward models could serve as one component of a data-driven articulatory synthesizer. The models also provide the first step toward building a model of spoken word acquisition and phonological development trained on real speech.

show abstract