The introduction of deep neural networks to acoustic modelling has brought significant improvements in speech recognition accuracy. However, this technology has huge computational costs, even when the algorithms are implemented on graphic processors. Hence, finding the right training algorithm that offers the best performance with the lowest training time is now an active area of research. Here...

This paper describes a framework for optimising the structure and parameters of a continuous density HMM-based large vocabulary recognition system using the Maximum Mutual Information Estimation (MMIE) criterion. To reduce the computational complexity of the MMIE training algorithm, confusable segments of speech are identified and stored as word lattices of alternative utterance hypotheses. An ...

The Nuisance Attribute Projection (NAP) with labeled data provides an effective approach for improving the speaker recognition performance in the state-of-art speaker recognition system by removing unwanted speaker channel and handsets variation. However, the requirement for the labeled NAP training data may limit its practical application. In this paper, we propose an unsupervised clustering s...

This paper describes a framework for optimising the structure and parameters of a continuous density HMM-based large Ž . vocabulary recognition system using the Maximum Mutual Information Estimation MMIE criterion. To reduce the computational complexity of the MMIE training algorithm, confusable segments of speech are identified and stored as word lattices of alternative utterance hypotheses. A...

I n this paper, we address the problem of isolated word recognition of speech under various stressed speaking conditions. The niain objective is to formulate an alternate training algorithm for hidden Markov model recognition, which better characterizes actual speech production under stressed speaking styles such as slow, loud and Lombard effect, without the need for collecting such stressed sp...

This paper addresses the issue of learning hidden Markov model (HMM) parameters for speaker-independent continuous speech recognition. Bahl et al. [Bahl 88a] introduced the corrective training algorithm for speaker-dependent isolated word recognition. Their algorithm attempted to improve the recognition accuracy on the training data. In this work, we extend this algorithm to speaker-independent...

Speech recognition systems are expensive to train, mostly due to the high cost of annotating training data. We previously proposed an iterative training algorithm [1], which sought to improve speech recognition by automatically selecting a subset of the available humanly transcribed training data, thereby improving error rates without incurring additional transcription cost. We suggest one impr...

In this paper, we report a study on performance comparisons of discriminative training methods for phone recognition using the TIMIT database. We propose a new method of phonediscriminating minimum classification error (P-MCE), which performs MCE training at the sub-string or phone level instead of at the traditional string level. Aiming at minimizing the phone recognition error rate, P-MCE nev...

Word level training refers to the process of learning the parameters of a word recognition system based on word level criteria functions. Previously, researchers trained lexicon-driven handwritten word recognition systems at the character level individually. These systems generally use statistical or neural based character recognizers to produce character level confidence scores. In the case of...