1 |
Dealing with linguistic mismatches for automatic speech recognition
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Semi-supervised learning for acoustic and prosodic modeling in speech applications
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Beiträge zur statistischen Modellierung und effizienten Dekodierung in der automatischen Spracherkennung ; Contributions to statistical modeling and effecient decoding in automatic speech recognition
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Automatic Recognition of Cantonese-English Code-Mixing Speech
|
|
|
|
In: http://wing.comp.nus.edu.sg/~antho/O/O09/O09-5003.pdf
|
|
BASE
|
|
Show details
|
|
5 |
COMBINING SPEECH RECOGNITION AND ACOUSTIC WORD EMOTION MODELS FOR ROBUST TEXT-INDEPENDENT EMOTION RECOGNITION
|
|
|
|
In: http://www.mmk.ei.tum.de/publ/pdf/08/08sch9.pdf
|
|
BASE
|
|
Show details
|
|
6 |
Towards a non-parametric acoustic model: An acoustic decision tree for observation probability calculation,” Interspeech 2008
|
|
|
|
In: http://www.cs.cmu.edu/~ychiu/ychiu_web_files/nonparametric.pdf
|
|
Abstract:
Modern automatic speech recognition systems use Gaussian mixture models (GMM) on acoustic observations to model the probability of producing a given observation under any one of many hidden discrete phonetic states. This paper investigates the feasibility of using an acoustic decision tree to directly model these probabilities. Unlike the more common phonetic decision tree, which asks questions about phonetic context, an acoustic decision tree asks questions about the vector-valued observations. Three different types of acoustic questions are proposed and evaluated, including LDA, PCA, and MMI questions. Frame classification experiments are run on a subset of the Switchboard corpus. On these experiments, the acoustic decision tree produces slightly better results than maximum likelihood trained GMMs, with significantly less computation. Some theoretical advantages of the acoustic decision tree are discussed, including more economical use of the training data and reduced mismatch between the acoustic model and the true probability distribution of the phonetic labels.
|
|
Keyword:
Acoustic Modeling; Decision Trees; Index Terms—Speech Recognition
|
|
URL: http://www.cs.cmu.edu/~ychiu/ychiu_web_files/nonparametric.pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.6754
|
|
BASE
|
|
Hide details
|
|
7 |
INTEGRATION OF MULTIPLE FEATURE SETS FOR REDUCING AMBIGUITY IN ASR
|
|
|
|
In: http://www.ece.mcgill.ca/~rrose1/papers/rose_parya_icassp07.pdf
|
|
BASE
|
|
Show details
|
|
8 |
Towards a Non-Parametric Acoustic Model: An Acoustic Decision Tree for Observation Probability Calculation
|
|
|
|
In: http://research.microsoft.com/pubs/78716/ADT.pdf
|
|
BASE
|
|
Show details
|
|
|
|