— This paper describes our work on Bengali Part of Speech (POS) tagging using a corpus-based approach. There are several approaches for part of speech tagging. This paper deals with a model that uses a combination of supervised and unsupervised learning using a Hidden Markov Model (HMM). We make use of small tagged corpus and a large untagged corpus. We also make use of Morphological Analyzer. ...

This research extends the range of domains within which children's gestures are found to play an important role in learning. The study involves children learning about balance, and the authors locate children's gestures within a relevant model of cognitive development--the representational redescription model (A. Karmiloff-Smith, 1992). The speech and gestures of children explaining a balance t...

This paper describes unsupervised strategies for estimating relative accuracy differences between acoustic models or language models used for automatic speech recognition. To test acoustic models, the approach extends ideas used for unsupervised discriminative training to include a more explicit validation on held out data. To test language models, we use a dual interpretation of the same proce...

This paper presents a localist multimodal neural network that uses Hebbian learning to acquire one-word child language from child directed speech (CDS) comprising multiword utterances and queries in addition to one-word utterances. The model implements cross-situational learning between linguistic words used in child directed speech, the accompanying perceptual entities, conceptual relations an...

Listeners must accomplish two complementary perceptual feats in extracting a message from speech. They must discriminate linguistically-relevant acoustic variability and generalize across irrelevant variability. Said another way, they must categorize speech. Since the mapping of acoustic variability is language-specific, these categories must be learned from experience. Thus, understanding how,...

We describe an account of lexically guided tuning of speech perception based on interactive processing and Hebbian learning. Interactive feedback provides lexical information to prelexical levels, and Hebbian learning uses that information to retune the mapping from auditory input to prelexical representations of speech. Simulations of an extension of the TRACE model of speech perception are pr...

This paper proposes an approach to automatically evaluate the prosody of Chinese Mandarin speech for language learning. In this approach, we grade the appropriateness of prosody of speech units according to a model speech corpus from a teacher’s voice. To this end, we build two models, which are the prosody model and the scoring model. The prosody model that is built from the teacher’s speech p...

In this paper, we present our investigation on using supervised machine learning methods to automatically classify online chat posts into speech act categories, which are semantic categories indicating speakers’ intentions. Supervised machine learning methods presuppose the existence of annotated training data based on which machine learning algorithms can be used to learn the parameters of som...

This paper proposes a text-to-speech synthesis (TTS) system based on a combined model consisting of the Composite Wavelet Model (CWM) and the Hidden Markov Model (HMM). Conventional HMM-based TTS systems using cepstral features tend to produce over-smoothed spectra, which often result in muffled and buzzy synthesized speech. This is simply caused by the averaging of spectra associated with each...