Search

The paper examines techniques that allow a well-trained source system built on one task to be rapidly adapted, or ported, to another target task. The two tasks considered are Hub5, or SwitchBoard, as the source system and VoiceMail as the target task. The two tasks are acoustically similar, both being telephone-bandwidth speech tasks, but differ in speaking style. SwitchBoard is conversational speech, VoiceMail is a set of voicemail messages. Various porting schemes for acoustic models are examined, including discriminative MAP and heteroscedastic LDA. Using around 28 hours of data, the error rate on VoiceMail was reduced by 42% relative compared to the baseline SwitchBoard performance.

Investigates the use of discriminative training techniques for large vocabulary speech recognition with training datasets up to 265 hours. Techniques for improving lattice-based maximum mutual information estimation (MMIE) training are described and compared to frame discrimination (FD). An objective function which is an interpolation of MMIE and standard maximum likelihood estimation (MLE) is also discussed. Experimental results on both the Switchboard and North American Business News tasks show that MMIE training can yield significant performance improvements over standard MLE even for the most complex speech recognition problems with very large training sets.

Discusses new features integrated into the Cambridge University HTK (CU-HTK) system for the transcription of conversational telephone speech. Major improvements have been achieved by the use of maximum mutual information estimation in training as well as maximum likelihood estimation; the use of a full variance transform for adaptation; the inclusion of unigram pronunciation probabilities; and word-level posterior probability estimation using confusion networks for use in minimum word error rate decoding, confidence score estimation and system combination. Improvements are demonstrated via performance on the NIST March 2000 evaluation of English conversational telephone speech transcription (Hub5E). In this evaluation the CU-HTK system gave an overall word error rate of 25.4%, which was the best performance by a statistically significant margin.

In this paper we introduce the Minimum Phone Error (MPE) and Minimum Word Error (MWE) criteria for the discriminative training of HMM systems. The MPE/MWE criteria are smoothed approximations to the phone or word error rate respectively. We also discuss I-smoothing which is a novel technique for smoothing discriminative training criteria using statistics for maximum likelihood estimation (MLE). Experiments have been performed on the Switchboard/Call Home corpora of telephone conversations with up to 265 hours of training data. It is shown that for the maximum mutual information estimation (MMIE) criterion, I-smoothing reduces the word error rate (WER) by 0.4% absolute over the MMIE baseline. The combination of MPE and I-smoothing gives an improvement of 1 % over MMIE and a total reduction in WER of 4.8% absolute over the original MLE system.

In this paper, we investigate alternative ways of processing MFCC-based features to use as the input to Deep Neural Networks (DNNs). Our baseline is a conventional feature pipeline that involves splicing the 13-dimensional front-end MFCCs across 9 frames, followed by applying LDA to reduce the dimension to 40 and then further decorrelation using MLLT. Confirming the results of other groups, we show that speaker adaptation applied on the top of these features using feature-space MLLR is helpful. The fact that the number of parameters of a DNN is not strongly sensitive to the input feature dimension (unlike GMM-based systems) motivated us to investigate ways to increase the dimension of the features. In this paper, we investigate several approaches to derive higher-dimensional features and verify their performance with DNN. Our best result is obtained from splicing our baseline 40-dimensional speaker adapted features again across 9 frames, followed by reducing the dimension to 200 or 300 using another LDA. Our final result is about 3% absolute better than our best GMM system, which is a discriminatively trained model.

Sequence-discriminative training of deep neural networks (DNNs) is investigated on a standard 300 hour American En- glish conversational telephone speech task. Different sequence- discriminative criteria — maximum mutual information (MMI), minimum phone error (MPE), state-level minimum Bayes risk (sMBR), and boosted MMI — are compared. Two different heuristics are investigated to improve the performance of the DNNs trained using sequence-based criteria — lattices are re- generated after the first iteration of training; and, for MMI and BMMI, the frames where the numerator and denominator hy- potheses are disjoint are removed from the gradient compu- tation. Starting from a competitive DNN baseline trained us- ing cross-entropy, different sequence-discriminative criteria are shown to lower word error rates by 7-9% relative, on aver- age. Little difference is noticed between the different sequence- based criteria that are investigated. The experiments are done using the open-source Kaldi toolkit, which makes it possible for the wider community to reproduce these results. Index Terms: speech recognition, deep learning, sequence- criterion training, neural networks, reproducible research

We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space. We call this a Subspace Gaussian Mixture Model (SGMM). Globally shared parameters define the subspace. This style of acoustic model allows for a much more compact representation and gives better results than a conventional modeling approach, particularly with smaller amounts of training data.

In this paper we present a novel approach for estimating feature-space maximum likelihood linear regression (fMLLR) transforms for full-covariance Gaussian models by directly maximizing the likelihood function by repeated line search in the direction of the gradient. We do this in a pre-transformed parameter space such that an approximation to the expected Hessian is proportional to the unit matrix. The proposed algorithm is as efficient or more efficient than standard approaches, and is more flexible because it can naturally be combined with sets of basis transforms and with full covariance and subspace precision and mean (SPAM) models.