Titlebook: Speech Recognition and Coding; New Advances and Tre Antonio J. Rubio Ayuso,Juan M. López Soler Conference proceedings 1995 Springer-Verlag

Estimable

0258-1248 topics were complemented with discussions and presentations of the work of those attending. Altogether, the reader is given a wide perspective on recent advances in the field and will be able to see the trends for future work.978-3-642-63344-7978-3-642-57745-1Series ISSN 0258-1248

急性

Statistical and Discriminative Methods for Speech Recognitioneech recognition. We show the superiority of the discriminative method over the distribution estimation method by citing the results of several key speech recognition experiments. In general, the discriminative method provides a 30-50% reduction in recognition errors.

flammable

摘要记录

Conference proceedings 1995 contains contributions by many of the most outstanding researchers from the best laboratories worldwide in the field. The contributions have been grouped into five parts: on acoustic modeling; language modeling; speech processing, analysis and synthesis; speech coding; and vector quantization and n

土产

Automatic Recognition of Noisy Speech training and testing conditions (noise level as measured by the signal-to-noise ratio, SNR,distance to the microphone and orientation, etc.), If trainingand testing can be carried in the same difficult conditions, performances turn out to be significantly better than that obtained when training is noise-free.

有偏见

Adaptive Learning in Acoustic and Language Modelingessing. The MAP formulation offers a way to combine existing prior knowledge and a small set of newly acquired task-specific data in an optimal manner. It is therefore ideal for adaptive learning applications such as speaker and task adaptation.

动物

适宜

An Efficient Pruning Algorithm for Continuous Speech Recognitionh is time-synchronous but in this case the active candidates at each given time . are pruned once all their paths at a time . > . are known, that is, the search space reduction is caused by the future behavior of the active nodes.

fleeting

ZEST

HMM Based Acoustic-Phonetic Decoding with Constrained Transitions and Speaker Topologyew decoding system using these two processings is compared with a standard HMM-based system on the TIMIT database. -A significant 4% improvement of the accuracy rate is observed on the 7000 test phonemes.