Emotions are essential in developing interpersonal relationships. make emphasizing with others’ problems easy and leads to better communication without misunderstandings. Humans possess the natural ability of understanding emotions from their speech, hand gestures, facial expressions etc react accordingly but, it is impossible for machines extract understand unless they trained do so. Speech Em...

More than two decades of work in vision posits the existence of dual-learning systems of category learning. The reflective system uses working memory to develop and test rules for classifying in an explicit fashion, while the reflexive system operates by implicitly associating perception with actions that lead to reinforcement. Dual-learning systems models hypothesize that in learning natural c...

We propose a novel scheme to learn a language model (LM) for automatic speech recognition (ASR) directly from continuous speech. In the proposed method, we first generate phoneme lattices using an acoustic model with no linguistic constraints, then perform training over these phoneme lattices, simultaneously learning both lexical units and an LM. As a statistical framework for this learning pro...

Newly born infants are able to finely discriminate almost all human speech contrasts and their phonemic category boundaries are initially identical, even for phonemes outside their target language. A connectionist model is described which accounts for this ability. The approach taken has been to develop a model of innately guided learning in which an artificial neural network (ANN) is stored in...

Newly born infants are able to nely discriminate almost all human speech contrasts and their phonemic category boundaries are initially identical, even for phonemes outside their target language. A connectionist model is described which accounts for this ability. The approach taken has been to develop a model of innately guided learning in which an artiicial neu-ral network (ANN) is stored in a...

We present a distributed framework for largescale discriminative language models that can be integrated within a large vocabulary continuous speech recognition (LVCSR) system using lattice rescoring. We intentionally use a weakened acoustic model in a baseline LVCSR system to generate candidate hypotheses for voice-search data; this allows us to utilize large amounts of unsupervised data to tra...

Background: Development of the feedback loop of speech production starts during the babbling phase of speech acquisition. Within the first year of lifetime toddlers acquire the ability of imitating auditory stimuli, i.e. they acquire the ability of associating speech-like sensory and motor states. Method: Self-organizing maps and one-layer feed-forward networks were used for modeling this learn...

Previous research has shown that a lexicalized parsing model incorporating words but no parts-of-speech can outperform a model involving partsof-speech but no words given enough training data for supervised learning. We show that the same effect can be achieved with a bootstrapping approach, where a mixed model trained on a small treebank is used to parse a larger corpus which is used as traini...

Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would otherwise be too complicated. On the other hand, deep learning based enhancement approaches are able to learn complicated speech distributions and perform e...