The Rational Speech Acts (RSA) model treats language use as a recursive process in which probabilistic speaker and listener agents reason about each other’s intentions to enrich the literal semantics of their language along broadly Gricean lines. RSA has been shown to capture many kinds of conversational implicature, but it has been criticized as an unrealistic model of speakers, and it has so ...

This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using acoustic model scores, and Bayesian techniques are used to robustly learn a language model from this noisy input. A novel sampling technique is devised that allows for the integrated learning of word boundaries and an...

education has stepped to an ultra-place and time in 21st century. we have entered to digital and wireless communication century which mobile technologies have changed the process of education and instruction. the application of these mobile technologies for creation of knowledge, attitude and skill in learners is called mobile learning. the effectiveness of mobile learning programs requires new...

The applicability of Flege’s Speech Learning Model (SLM) to simultaneous bilinguals is examined in related experiments on the acquisition of the production and perception of the voicing contrast in simultaneous French-English bilinguals. The results show that the SLM can account for the data providing account is taken of the degree of bilinguals’ exposure to each language.

The influence of a native language on learning new speech sounds in adulthood is addressed using a network model in which speech categories are attractors implemented through interactive activation and Hebbian learning. The network has a representation layer that receives topographic projections from an input layer and has reciprocal excitatory connections with deeper layers. When applied to an...

In this paper, we address the problem of evaluating spontaneous speech using a combination of machine learning and crowdsourcing. Machine learning techniques inadequately solve the stated problem because automatic speakerindependent speech transcription is inaccurate. The features derived from it are also inaccurate and so is the machine learning model developed for speech evaluation. To addres...

Speech separation can be formulated as learning to estimate a time-frequency mask from acoustic features extracted from noisy speech. For supervised speech separation, generalization to unseen noises and unseen speakers is a critical issue. Although deep neural networks (DNNs) have been successful in noise-independent speech separation, DNNs are limited in modeling a large number of speakers. T...

For a Chinese speech synthesis system, hierarchical prosody structure generation is a key component. The prosodic word, which is the basic prosodic unit, plays an important role in the naturalness and intelligibility of Chinese Text-To-Speech system. However, obtaining human annotations of prosodic words to train a supervised system can be a laborious and costly effort. To overcome this, we exp...

This paper reports the on-going research of a thesis project investigating a computational model of early language acquisition. The model discovers word-like units from crossmodal input data and builds continuously evolving internal representations within a cognitive model of memory. Current cognitive theories suggest that young infants employ general statistical mechanisms that exploit the sta...