Revisiting Word Neighborhoods for Speech Recognition Preethi Jyothi∗ Beckman Institute University of Illinois, Urbana, IL

Source URL: ttic.uchicago.edu

SIGNAL PROCESSING MAGAZINE, VOL. XX, NO. YY, ZZZZ 1 Sub-word modeling for automatic speech recognition

Source URL: ttic.uchicago.edu

Are we using enough listeners? No! An empirically-supported critique of Interspeech 2014 TTS evaluations Mirjam Wester, Cassia Valentini-Botinhao, Gustav Eje Henter The Centre for Speech Technology Research, University o

Source URL: www.cstr.ed.ac.uk

• Human communication
• Computational linguistics
• Linguistics
• Psychophysics
• Phonetics
• Academia
• Audio codecs
• Acoustics
• MUSHRA
• Mean opinion score
• Speech synthesis
• Speech recognition

MODELING PRONUNCIATION VARIATION FOR SPEECH RECOGNITION A THESIS submitted by

Source URL: ravi.iiit.ac.in

arXiv:1411.4555v2 [cs.CV] 20 AprShow and Tell: A Neural Image Caption Generator Oriol Vinyals Google

Source URL: arxiv.org

• Artificial neural networks
• Machine learning
• Applied mathematics
• Computational neuroscience
• Artificial intelligence
• Computational linguistics
• Machine translation
• Deep learning
• Recurrent neural network
• Long short-term memory
• Speech recognition
• Language model

Grid Long Short-Term Memory Nal Kalchbrenner Ivo Danihelka

Source URL: arxiv.org

• Artificial neural networks
• Machine learning
• Applied mathematics
• Cybernetics
• Long short-term memory
• Recurrent neural network
• Speech recognition
• Vanishing gradient problem
• Artificial intelligence
• Backpropagation
• Dimension
• Deep learning

Cocaine Noodles: Exploiting the Gap between Human and Machine Speech Recognition∗ Tavish Vaidya Georgetown University Yuankai Zhang

Source URL: security.cs.georgetown.edu

• Computational linguistics
• Speech recognition
• Mel-frequency cepstrum
• Speech synthesis
• Speech processing
• Deep learning
• Perception
• Acoustic model

You, Jike Chong, Youngmin Yi, Ekaterina Gonina, [Kisun Christopher J. Hughes, Yen-Kuang Chen, Wonyong Sung, and Kurt Keutzer] Parallel Scalability in Speech Recognition

Source URL: pcl.intel-research.net

Hidden Feature Models for Speech Recognition Using Dynamic Bayesian Networks Karen Livescu, James Glass Jeff Bilmes

Source URL: ttic.uchicago.edu

SIGNIFICANCE OF EARLY TAGGED CONTEXTUAL GRAPHEMES IN GRAPHEME BASED SPEECH SYNTHESIS AND RECOGNITION SYSTEMS Gopala Krishna Anumanchipalli†, Kishore Prahallad † ‡ and Alan W Black ‡ ‡ Language Technologies Inst

Source URL: ravi.iiit.ac.in