Motivated by the fact that the pronunciation of a name may be influenced by its language of origin, we present methods to improve pronunciation prediction of proper names using word origin information. We train grapheme-to-phoneme (G2P) models on language-specific data sets and interpolate the outputs. We perform experiments on US surnames, a data set where word origin variation occurs naturall...

Children with developmental disabilities such as childhood apraxia of speech (CAS) require repeated intervention sessions with a speech therapist, sometimes extending over several years. Technology-based therapy tools offer the potential to reduce the demanding workload of speech therapists as well as time and cost for families. In response to this need, we have developed “Tabby Talks,” a multi...

Generating pronunciation variants of words is an important subject in speech research and is used extensively in automatic speech recognition and segmentation systems. Decision trees are well known tools in modeling pronunciation over words or sub-word units. In the case of word units and very large vocabulary, in order to train necessary decision trees, a huge amount of speech utterances are r...

word word P(w) (decision tree) model Although finite-state transducers have been widely used in linguistics, their application to speech recognition has begun only recently [I]. We describe our implementation of French large vocabulary recognition based on transducers, and how we take advantage of this approach to integrate automatic pronunciation rules and cross-word phenomena such as French '...

The errors in Chinese document are mainly caused in two stages input and editing. There are homonyms or homophones selection error, ambiguous pronunciation error, word segmentation error, similar shape character error, editing operation error and so on. In order to increase the quality of Chinese text, the conventional Chinese document revision system used the similar characters set and languag...

French is known to be a language with major pronunciation irregularities at word endings with consonants. Particularly, the well-known phonetic phenomenon called Liaison is one of the major issues for French phonetizers. Rule-based methods have been used to solve these issues. Yet, the current models still produce a great number of pronunciation errors to be used in 2nd language learning applic...

We investigate the detection of spoken terms in conversational speech using phoneme recognition with the objective of achieving smaller index size as well as faster search speed. Speech is processed and indexed as a sequence of one best phoneme sequence. We propose the use of a probabilistic pronunciation model for the search term to compensate for the errors in the recognition of phonemes. Thi...

This paper presents a method for incorporating word pronunciation information in a noisy channel model for spelling correction. The proposed method builds an explicit error model for word pronunciations. By modeling pronunciation similarities between words we achieve a substantial performance improvement over the previous best performing models for spelling correction.

In this paper, we propose to use Deep Neural Net (DNN), which has been recently shown to reduce speech recognition errors significantly, in Computer-Aided Language Learning (CALL) to evaluate English learners’ pronunciations. Multi-layer, stacked Restricted Boltzman Machines (RBMs), are first trained as nonlinear basis functions to represent speech signals succinctly, and the output layer is di...