IEEE Signal Processing Letters · 2010 · 15 citations · 17 references
ComputingComputer ScienceFeature EngineeringMachine LearningPhoneticsAcoustic PhoneticsPattern RecognitionSpeech AcousticsSpeech RecognitionTime Series Feature ExtractionAudio Feature ExtractionAutomatic RecognitionMultilayer PerceptronPhoneme RecognitionSpectral Analysis Of SpeechSpeech Pattern RecognitionSpeech Recognition AcousticsTemporal Feature Extraction
This paper proposes novel data-driven and feedback based discriminative spectro-temporal filters for feature extraction in automatic speech recognition (ASR). Initially a first set of spectro-temporal filters are designed to separate each phoneme from the rest of the phonemes. A hybrid Hidden Markov Model/Multilayer Perceptron (HMM/MLP) phoneme recognition system is trained on the features derived using these filters. As a feedback to the feature extraction stage, top confusions of this system are identified, and a second set of filters are designed specifically to address these confusions. Phoneme recognition experiments on TIMIT show that the features derived from the combined set of discriminative filters outperform conventional speech recognition features, and also contain significant complementary information.
17
Improved boosting algorithms using confidence-rated predictions
Robert E. Schapire, Yoram Singer · 1998 · 2.6K citations