Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
Pourquoi ce travail est-il dans la base ?
Une base qui oublie comment elle a trouvé un travail ne peut pas être vérifiée. Voici les voies qui ont admis celui-ci.
Résumé
Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input. An alternative way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition benchmarks, sometimes by a large margin. This article provides an overview of this progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
La notice
- Revue
- IEEE Signal Processing Magazine
- Thématique
- Speech Recognition and Synthesis
- Domaine
- Computer Science
- Établissements canadiens
- University of WaterlooUniversity of Toronto
- Organismes subventionnaires
- —
- Mots-clés
- Hidden Markov modelSpeech recognitionComputer scienceMixture modelArtificial neural networkMargin (machine learning)Deep neural networksPattern recognition (psychology)Frame (networking)Artificial intelligenceAcoustic modelGaussianSpeech processingMachine learning
- Résumé présent dans OpenAlex
- oui