Interpolation of n-gram and mutual-information based trigger pair language models for Mandarin speech recognition

AbstractWe propose a method of dynamically registering out-of-vocabulary (OOV) words by assigning the pronunciations of these words to pre-inserted OOV tokens, editing the pronunciations of the tokens. To do this, we add OOV tokens to an additional, partial copy of our corpus, either randomly or to part-of-speech (POS) tags in the selected utterances, when training the language model (LM) for speech recognition. This results in an LM containing OOV tokens, to which we can assign pronunciations. We also investigate the impact of acoustic complexity and the “natural” occurrence frequency of OOV words on the recognition of registered OOV words. The proposed OOV word registration method is evaluated using two modern automatic speech recognition (ASR) systems, Julius and Kaldi, using DNN-HMM acoustic models and N-gram language models (plus an additional evaluation using RNN re-scoring with Kaldi). Our experimental results show that when using the proposed OOV registration method, modern ASR systems can recognize OOV words without re-training the language model, that the acoustic complexity of OOV words affects OOV recognition, and that differences between the “natural” and the assigned occurrence frequencies of OOV words have little impact on the final recognition results.

Download Full-text

Discriminative training of n-gram language models for speech recognition via linear programming

2009 IEEE Workshop on Automatic Speech Recognition & Understanding ◽

10.1109/asru.2009.5373248 ◽

2009 ◽

Cited By ~ 3

Author(s):

Vladi Magdin ◽

Hui Jiang

Keyword(s):

Linear Programming ◽

Speech Recognition ◽

Discriminative Training ◽

Language Models ◽

N Gram

Download Full-text

Using morphemes in language modeling and automatic speech recognition of Amharic

Natural Language Engineering ◽

10.1017/s1351324912000356 ◽

2012 ◽

Vol 20 (2) ◽

pp. 235-259 ◽

Cited By ~ 1

Author(s):

MARTHA YIFIRU TACHBELIE ◽

SOLOMON TEFERRA ABATE ◽

WOLFGANG MENZEL

Keyword(s):

Speech Recognition ◽

Substantial Reduction ◽

Recognition Task ◽

Recognition System ◽

Language Modeling ◽

Language Models ◽

Vocabulary Size ◽

Severe Problem ◽

Morphologically Rich Languages ◽

N Gram

AbstractThis paper presents morpheme-based language models developed for Amharic (a morphologically rich Semitic language) and their application to a speech recognition task. A substantial reduction in the out of vocabulary rate has been observed as a result of using subwords or morphemes. Thus a severe problem of morphologically rich languages has been addressed. Moreover, lower perplexity values have been obtained with morpheme-based language models than with word-based models. However, when comparing the quality based on the probability assigned to the test sets, word-based models seem to fare better. We have studied the utility of morpheme-based language models in speech recognition systems and found that the performance of a relatively small vocabulary (5k) speech recognition system improved significantly as a result of using morphemes as language modeling and dictionary units. However, as the size of the vocabulary increases (20k or more) the morpheme-based systems suffer from acoustic confusability and did not achieve a significant improvement over a word-based system with an equivalent vocabulary size even with the use of higher order (quadrogram) n-gram language models.

Download Full-text