Language learning is a relatively new application for natural language processing (NLP) and for intelligent tutoring and learning environments (ITLEs). NLP has a crucial role to play in foreign language ITLEs, whether they are designed for explicit or implicit learning of the vocabulary and grammar. FLUENT is an implicit approach, in which NLP and sharedcontrol animation support a two-medium co...

Automatic speech recognition systems are prone to errors when there are confusable words in the dictionary. Even human beings sometimes make errors when they have to choose between words like “fix” and “six”. The situation is worse for telephone conversation. Most unvoiced phonemes with low energy are lost in the background noise. In this paper, a new approach to the solution of this problem is...

A comparison of human speech recognition (HSR) and automatic speech recognition (ASR) is presented using a noisy continuous-speech corpus of null grammar or uniformly distributed unigram sentences, focusing on the differential tendency of machines vs. humans to propagate errors from an unclear phone to its neighbors. It is shown using controlled experiments that when given the same context for ...

In automatic speech recognition on mobile devices, very often what a user says strongly depends on the particular context he or she is in. The n-grams relevant to the context are often not known in advance. The context can depend on, for example, particular dialog state, options presented to the user, conversation topic, location, etc. Speech recognition of sentences that include these n-grams ...

Designers of spoken dialogue systems need to be able to predict and constrain the words people use in speech directed at these systems. Larger vocabularies lead to longer processing times, as well as a substantial increase in perplexity errors; according to one estimate (Makhoul 1993), error rates increase with the square root of the number of words in the vocabulary (assuming all words are equ...

objectives: one of the factors predicting language impairments is an early limited lexicon in children. an early limited lexicon can also lead to limited performances in other language areas. this study was aimed to examine receptive and expressive vocabulary in 8-16 month-old children with cleft lip and palate as a predictor of development in other language areas. materials: the macarthur-bate...

Studies of human continuous-speech recognition suggest that Iistencrs use a strategy of postulating a word boundary, and initiating a lexical access procedure, at each metrically strong syllable. The likely success of this strategy was here estimated against the characteristics of the English vocabulary. Computerised dictionaries of Engtish were found to Iist approximately three times as many w...

Emotional intelligence is one of the key factors to the success of dialogue systems or conversational agents. In this paper, we propose Emotional Chatting Machine (ECM) which generates responses that are appropriate not only at the content level (relevant and grammatical) but also at the emotion level (consistent emotional expression). To the best of our knowledge, this is the first work that a...

Opportunities for incidental vocabulary acquisition were explored in a 121,000-word corpus of teacher talk addressed to advanced adult learners of English as a second language (ESL) in a communicatively-oriented conversation class. In contrast to previous studies that relied on short excerpts, the corpus contained all of the teacher speech the learners were exposed to during a 9-week session. L...

We present an approach to speech recognition that uses only a neural network to map acoustic input to characters, a character-level language model, and a beam search decoding procedure. This approach eliminates much of the complex infrastructure of modern speech recognition systems, making it possible to directly train a speech recognizer using errors generated by spoken language understanding ...