Search

This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 2.5 machine translation evaluation. Key advances include the use of additional training data from the Linguistic Data Consortium (LDC), use of a very large vocabulary comprising 737 K words and 2.5 M pronunciation variants, automatic vowelization using flat-start training, cross-adaptation between unvowelized and vowelized acoustic models, and rescoring with a neural-network language model. The resulting system achieves word error rates below 10% on Arabic broadcasts. Very large scale experiments with unsupervised training demonstrate that the utility of unsupervised data depends on the amount of supervised data available. While unsupervised training improves system performance when a limited amount (135 h) of supervised data is available, these gains disappear when a greater amount (848 h) of supervised data is used, even with a very large (7069 h) corpus of unsupervised data. We also describe a method for modeling Arabic dialects that avoids the problem of data sparseness entailed by dialect-specific acoustic models via the use of non-phonetic, dialect questions in the decision trees. We show how this method can be used with a statically compiled decoding graph by partitioning the decision trees into a static component and a dynamic component, with the dynamic component being replaced by a mapping that is evaluated at run-time.

Data augmentation is a common strategy adopted to increase the quantity of training data, avoid overfitting and improve robustness of the models. In this paper, we investigate audio-level speech augmentation methods which directly process the raw signal. The method we particularly recommend is to change the speed of the audio signal, producing 3 versions of the original signal with speed factors of 0.9, 1.0 and 1.1. The proposed technique has a low implementation cost, making it easy to adopt. We present results on 4 different LVCSR tasks with training data ranging from 100 hours to 1000 hours, to examine the effectiveness of audio augmentation in a variety of data scenarios. An average relative improvement of 4.3% was observed across the 4 tasks.

In reverberant environments there are long term interactions between speech and corrupting sources. In this paper a time delay neural network (TDNN) architecture, capable of learning long term temporal relationships and translation invariant representations, is used for reverberation robust acoustic modeling. Further, iVectors are used as an input to the neural network to perform instantaneous speaker and environment adaptation, providing 10% relative improvement in word error rate. By subsampling the outputs at TDNN layers across time steps, training time is reduced. Using a parallel training algorithm we show that the TDNN can be trained on ∼ 5500 hours of speech data in 3 days using up to 32 GPUs. The TDNN is shown to provide results competitive with state of the art systems in the IARPA ASpIRE challenge, with 27.7% WER on the dev test set.

A common way to improve the performance of deep learning is to train an ensemble of neural networks and combine them during decoding. However, this is computationally expensive in test time. In this paper, we propose an diversity-penalizing ensemble training (DPET) procedure, which trains an ensemble of DNNs, whose parameters were differently initialized, and penalizes differences between each individual DNN’s output and their average output. This way each model learns to emulate the average of the whole ensemble of models, and in test time we can use one arbitrarily chosen member of the ensemble. Experimental results on a variety of speech recognition tasks show that this technique is effective, and gives us most of the WER improvement of the ensemble method while being no more expensive in test time than using a single model.

Modern speech recognition systems typically cluster triphone phonetic contexts using decision trees. In this paper we describe a way to build multiple complementary decision trees from the same data, for the purpose of system combination. We do this by jointly building the decision trees using an objective function that has an added entropy term to encourage diversity among the decision trees. After the trees are built, the systems are built in the standard way and the emission probabilities are combined during decoding. Experiments on multiple datasets show gains from the use of multiple trees, at the expense of evaluating multiple models in test time.

Maximum Mutual Information (MMI) is a popular discriminative criterion that has been used in supervised training of acoustic models for automatic speech recognition. However, standard discriminative training is very sensitive to the accuracy of the transcription and hence its implementation in a semisupervised setting requires extensive filtering of data. We will show that if the supervision transcripts are not known, the natural analogue of MMI is to minimize the conditional entropy of the lattice of possible transcripts of the data. This is equivalent to the weighted average of MMI criterion over different reference transcripts, taking those reference transcripts and their weighting from the lattice itself. In this paper we describe experiments where we applied this method to the semi-supervised training of Deep Neural Network acoustic models. In our experimental setup, the proposed method gives up to 0.5% absolute WER improvement over a DNN trained with sMBR only on the transcribed part of the data. This is 37% of the improvement that we would get from doing sMBR training if we had the transcripts for the untranscribed part of the data.

This paper introduces a new corpus of read English speech, suitable for training and evaluating speech recognition systems. The LibriSpeech corpus is derived from audiobooks that are part of the LibriVox project, and contains 1000 hours of speech sampled at 16 kHz. We have made the corpus freely available for download, along with separately prepared language-model training data and pre-built language models. We show that acoustic models trained on LibriSpeech give lower error rate on the Wall Street Journal (WSJ) test sets than models trained on WSJ itself. We are also releasing Kaldi scripts that make it easy to build these systems.

Speech translation is conventionally carried out by cascading an automatic speech recognition (ASR) and a statistical machine translation (SMT) system. The hypotheses chosen for translation are based on the ASR system’s acoustic and language model scores, and typically optimized for word error rate, ignoring the intended downstream use: automatic translation. In this paper, we present a coarseto-fine model that uses features from the ASR and SMT systems to optimize this coupling. We demonstrate that several standard features utilized by ASR and SMT systems can be used in such a model at the speech-translation interface, and we provide empirical results on the Fisher Spanish-English speech translation corpus.

This paper describes the technical and system building advances made in IBM's speech recognition technology over the course of the Defense Advanced Research Projects Agency (DARPA) Effective Affordable Reusable Speech-to-Text (EARS) program. At a technical level, these advances include the development of a new form of feature-based minimum phone error training (fMPE), the use of large-scale discriminatively trained full-covariance Gaussian models, the use of septaphone acoustic context in static decoding graphs, and improvements in basic decoding algorithms. At a system building level, the advances include a system architecture based on cross-adaptation and the incorporation of 2100 h of training data in every system component. We present results on English conversational telephony test data from the 2003 and 2004 NIST evaluations. The combination of technical advances and an order of magnitude more training data in 2004 reduced the error rate on the 2003 test set by approximately 21% relative-from 20.4% to 16.1%-over the most accurate system in the 2003 evaluation and produced the most accurate results on the 2004 test sets in every speed category

This paper discusses the Cambridge University HTK (CU-HTK) system for the automatic transcription of conversational telephone speech. A detailed discussion of the most important techniques in front-end processing, acoustic modeling and model training, language and pronunciation modeling are presented. These include the use of conversation side based cepstral normalization, vocal tract length normalization, heteroscedastic linear discriminant analysis for feature projection, minimum phone error training and speaker adaptive training, lattice-based model adaptation, confusion network based decoding and confidence score estimation, pronunciation selection, language model interpolation, and class based language models. The transcription system developed for participation in the 2002 NIST Rich Transcription evaluations of English conversational telephone speech data is presented in detail. In this evaluation the CU-HTK system gave an overall word error rate of 23.9%, which was the best performance by a statistically significant margin. Further details on the derivation of faster systems with moderate performance degradation are discussed in the context of the 2002 CU-HTK 10 /spl times/ RT conversational speech transcription system.

Spoken Term Detection (STD) focuses on finding instances of a particular spoken word or phrase in an audio corpus. Most STD systems have a two-step pipeline, ASR followed by search. Two approaches to search are common, Confusion Network (CN) based search and Finite State Transducer (FST) based search. In this paper, we examine combination of these two different search approaches, using the same ASR output. We find that the CN search performs better on shorter queries, and FST search performs better on longer queries. By combining the different search results from the same ASR decoding, we achieve better performance compared to either search approach on its own. We also find that this improvement is additive to the usual combination of decoder results using different modeling techniques.

Recently, maxout networks have brought significant improvements to various speech recognition and computer vision tasks. In this paper we introduce two new types of generalized maxout units, which we call p-norm and soft-maxout. We investigate their performance in Large Vocabulary Continuous Speech Recognition (LVCSR) tasks in various languages with 10 hours and 60 hours of data, and find that the p-norm generalization of maxout consistently performs well. Because, in our training setup, we sometimes see instability during training when training unbounded-output nonlinearities such as these, we also present a method to control that instability. This is the “normalization layer”, which is a nonlinearity that scales down all dimensions of its input in order to stop the average squared output from exceeding one. The performance of our proposed nonlinearities are compared with maxout, rectified linear units (ReLU), tanh units, and also with a discriminatively trained SGMM/HMM system, and our p-norm units with p equal to 2 are found to perform best.

Provides an overview of a speech-to-text (STT) and keyword search (KWS) system architecture build primarily on the top of the Kaldi toolkit and expands on a few highlights. The system was developed as a part of the research efforts of the Radical team while participating in the IARPA Babel program. Our aim was to develop a general system pipeline which could be easily and rapidly deployed in any language, independently on the language script and phonological and linguistic features of the language.

We propose a simple but effective weighted finite state transducer (WFST) based framework for handling out-of-vocabulary (OOV) keywords in a speech search task. State-of-the-art large vocabulary continuous speech recognition (LVCSR) and keyword search (KWS) systems are developed for conversational telephone speech in Tagalog. Word-based and phone-based indexes are created from word lattices, the latter by using the LVCSR system's pronunciation lexicon. Pronunciations of OOV keywords are hypothesized via a standard grapheme-to-phoneme method. In-vocabulary proxies (word or phone sequences) are generated for each OOV keyword using WFST techniques that permit incorporation of a phone confusion matrix. Empirical results when searching for the Babel/NIST evaluation keywords in the Babel 10 hour development-test speech collection show that (i) searching for word proxies in the word index significantly outperforms searching for phonetic representations of OOV words in a phone index, and (ii) while phone confusion information yields minor improvement when searching a phone index, it yields up to 40% improvement in actual term weighted value when searching a word index with word proxies.

In this paper, we show how new training principles and optimization techniques for neural networks can be used for different network structures. In particular, we revisit the Recurrent Neural Network (RNN), which explicitly models the Markovian dynamics of a set of observations through a non-linear function with a much larger hidden state space than traditional sequence models such as an HMM. We apply pretraining principles used for Deep Neural Networks (DNNs) and second-order optimization techniques to train an RNN. Moreover, we explore its application in the Aurora2 speech recognition task under mismatched noise conditions using a Tandem approach. We observe top performance on clean speech, and under high noise conditions, compared to multi-layer perceptrons (MLPs) and DNNs, with the added benefit of being a “deeper” model than an MLP but more compact than a DNN.

We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alternative transcriptions of an utterance. This method does not introduce substantial overhead above one-best decoding. Our method is most directly applicable when using WFST decoders where the WFST is “fully expanded”, i.e. where the arcs correspond to HMM transitions. It outputs lattices that include HMM-state-level alignments as well as word labels. The general idea is to create a state-level lattice during decoding, and to do a special form of determinization that retains only the best-scoring path for each word sequence. This special determinization algorithm is a solution to the following problem: Given a WFST A, compute a WFST B that, for each input-symbol-sequence of A, contains just the lowest-cost path through A.

We describe how to effectively train neural network based language models on large data sets. Fast convergence during training and better overall performance is observed when the training data are sorted by their relevance. We introduce hash-based implementation of a maximum entropy model, that can be trained as a part of the neural network model. This leads to significant reduction of computational complexity. We achieved around 10% relative reduction of word error rate on English Broadcast News speech recognition task, against large 4-gram model trained on 400M tokens.

Recently there has been some interest in the question of how to build LVCSR systems when there is only a limited amount of acoustic training data in the target language, but possibly more plentiful data in other languages. In this paper we investigate approaches using MLP based features. We experiment with two approaches: One is based on Automatic Speech Attribute Transcription (ASAT), in which we train classifiers to learn articulatory features. The other approach uses only the target-language data and relies on combination of multiple MLPs trained on different subsets. After system combination we get large improvements of more than 10% relative versus a conventional baseline. These feature-level approaches may also be combined with other, model-level methods for the multilingual or low-resource scenario.

Last year we introduced the Subspace Gaussian Mixture Model (SGMM), and we demonstrated Word Error Rate improvements on a fairly small-scale task. Here we describe an extension to the SGMM, which we call the symmetric SGMM. It makes the model fully symmetric between the “speech-state vectors” and “speaker vectors” by making the mixture weights depend on the speaker as well as the speech state. We had previously avoided this as it introduces difficulties for efficient likelihood evaluation and parameter estimation, but we have found a way to overcome those difficulties. We find that the symmetric SGMM can give a very worthwhile improvement over the previously described model. We will also describe some larger-scale experiments with the SGMM, and report on progress toward releasing open-source software that supports SGMMs.

Constrained Maximum Likelihood Linear Regression (CMLLR) is a widely used speaker adaptation technique in which an affine transform of the features is estimated for each speaker. However, when the amount of speech data available is very small (e.g. a few seconds), it can be difficult to get sufficiently accurate estimates of the transform parameters. In this paper we describe a method of estimating CMLLR robustly from less data. We do this by representing the CMLLR transform matrix as a weighted sum over basis matrices, where the basis is constructed in such a way that the most important variation is concentrated in the leading coefficients. Depending on the amount of data available, we can choose to estimate a smaller or larger number of coefficients.

Preparation of a lexicon for speech recognition systems can be a significant effort in languages where the written form is not exactly phonetic. On the other hand, in languages where the written form is quite phonetic, some common words are often mispronounced. In this paper, we use a combination of lexicon learning techniques to explore whether a lexicon can be learned when only a small lexicon is available for boot-strapping. We discover that for a phonetic language such as Spanish, it is possible to do that better than what is possible from generic rules or hand-crafted pronunciations. For a more complex language such as English, we find that it is still possible but with some loss of accuracy.

Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approach has been to use some kind of “universal phone set” that covers multiple languages. We report experiments on a different approach to multilingual speech recognition, in which the phone sets are entirely distinct but the model has parameters not tied to specific states that are shared across languages. We use a model called a “Subspace Gaussian Mixture Model” where states' distributions are Gaussian Mixture Models with a common structure, constrained to lie in a subspace of the total parameter space. The parameters that define this subspace can be shared across languages. We obtain substantial WER improvements with this approach, especially with very small amounts of in-language training data.

This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system include improved discriminative training, the use of Subspace Gaussian Mixture Models (SGMM), neural network acoustic features, variable frame rate decoding, training data partitioning experiments, unpruned n-gram language models and neural network language models. These advances were instrumental in achieving a word error rate of 8.9% on the evaluation test set.

In this paper we describe a method for Minimum Bayes Risk decoding for speech recognition. This is a technique similar to Consensus a.k.a. Confusion Network Decoding, in which we attempt to find the hypothesis that minimizes the Bayes' Risk with respect to the word error rate, based on a lattice of alternative outputs. Our method is an E-M like technique which makes approximations which we believe are less severe than the approximations made in Consensus, and our experimental results show an improvement in WER both for lattice rescoring and lattice-based system combination, versus baselines such as Consensus, Confusion Network Combination and ROVER.

This paper gives an up-to-date description of the IBM Mandarin broadcast transcription system developed under the DARPA GALE program. Technical advances over our previous system include a novel acoustic modeling approach using subspace Gaussian mixture models, a speaking rate adaptation method using frame rate normalization, and an effective recipe for lattice combination. We present results on three consortium-defined test sets. It is shown that with these advances, the new system attains a 9% relative reduction in character error rate compared to our previous GALE evaluation system. The reported 9.1% error rate on the phase three evaluation set represents the state of the art in Mandarin broadcast speech transcription.

In this paper we show how methods for approximating phone error as normally used for Minimum Phone Error (MPE) discriminative training, can be used instead as a decoding criterion for lattice rescoring. This is an alternative to Confusion Networks (CN) which are commonly used in speech recognition. The standard (Maximum A Posteriori) decoding approach is a Minimum Bayes Risk estimate with respect to the Sentence Error Rate (SER); however, we are typically more interested in the Word Error Rate (WER). Methods such as CN and our proposed Minimum Hypothesis Phone Error (MHPE) aim to get closer to minimizing the expected WER. Based on preliminary experiments we find that our approach gives more improvement than CN, and is conceptually simpler.

We discuss the applicability of large margin techniques to the problem of estimating linear transforms for discriminative training of a semi-tied covariance (STC) model. Since STC models are good proxies for full-covariance (FC) Gaussian models, the idea is to combine the benefit of the latest discriminative training techniques and the modeling advantage of FC Gaussians at a much lower computational cost. We study the interaction of these transforms with feature-space and model-space discriminative training on state-of-the-art speaker adapted systems built for a large-scale Arabic broadcast news transcription task.

The universal background model (UBM) is an effective framework widely used in speaker recognition. But so far it has received little attention from the speech recognition field. In this work, we make a first attempt to apply the UBM to acoustic modeling in ASR. We propose a tree-based parameter estimation technique for UBMs, and describe a set of smoothing and pruning methods to facilitate learning. The proposed UBM approach is benchmarked on a state-of-the-art large-vocabulary continuous speech recognition platform on a broadcast transcription task. Preliminary experiments reported in this paper already show very exciting results.

We present a modified form of the maximum mutual information (MMI) objective function which gives improved results for discriminative training. The modification consists of boosting the likelihoods of paths in the denominator lattice that have a higher phone error relative to the correct transcript, by using the same phone accuracy function that is used in Minimum Phone Error (MPE) training. We combine this with another improvement to our implementation of the Extended Baum-Welch update equations for MMI, namely the canceling of any shared part of the numerator and denominator statistics on each frame (a procedure that is already done in MPE). This change affects the Gaussian-specific learning rate. We also investigate another modification whereby we replace I-smoothing to the ML estimate with I-smoothing to the previous iteration's value. Boosted MMI gives better results than MPE in both model and feature-space discriminative training, although not consistently.

Feature space maximum likelihood linear regression (fMLLR) is a widely used technique for speaker adaptation in HMM-based speech recognition. However, in extremely resource constrained systems the time required to perform the sufficient statistics accumulation for fMLLR adaptation can be considerable. In this paper we describe a novel method that can lead to significant reduction in the time taken for statistics accumulation while preserving the adaptation gains. The proposed quick fMLLR (Q-fMLLR) algorithm is implemented in a state-of-the-art large-vocabulary continuous speech recognition system, and evaluated on a broadcast transcription task. We present results both in terms of the average likelihood after adaptation and the character error rate. It is shown that Q-fMLLR attains the performance of regular fMLLR with a fraction of the computation.

This paper describes the advances made in IBM's Arabic broadcast news transcription system which was fielded in the 2006 GALE ASR and machine translation evaluation. These advances were instrumental in lowering the word error rate by 42% relative over the course of one year and include: training on additional LDC data, large-scale discriminative training on 1800 hours of unsupervised data, automatic vowelization using a flat-start approach, use of a large vocabulary with 617K words and 2 million pronunciations and lastly, a system architecture based on cross-adaptation between unvowelized and vowelized acoustic models.

MPE (minimum phone error) is a previously introduced technique for discriminative training of HMM parameters. fMPE applies the same objective function to the features, transforming the data with a kernel-like method and training millions of parameters, comparable to the size of the acoustic model. Despite the large number of parameters, fMPE is robust to over-training. The method is to train a matrix projecting from posteriors of Gaussians to a normal size feature space, and then to add the projected features to normal features such as PLP. The matrix is trained from a zero start using a linear method. Sparsity of posteriors ensures speed in both training and test time. The technique gives similar improvements to MPE (around 10% relative). MPE on top of fMPE results in error rates up to 6.5% relative better than MPE alone, or more if multiple layers of transform are trained.

This paper describes the technical advances in IBM's conversational telephony submission to the DARPA-sponsored 2004 rich transcription evaluation (RT-04). These advances include a system architecture based on cross-adaptation; a new form of feature-based MPE training; the use of a full-scale discriminatively trained full covariance Gaussian system; the use of septaphone cross-word acoustic context in static decoding graphs; and the incorporation of 2100 hours of training data in every system component. These advances reduced the error rate by approximately 21% relative, on the 2003 test set, over the best-performing system in last year's evaluation, and produced the best results on the RT-04 current and progress CTS data.

In this paper, we concentrate on Arabic speech recognition. Taking advantage of the rich morphological structure of the language, we use morpheme-based language modeling to improve the word error rate. We propose a simple constraining method to rid the decoding output of illegal morpheme sequences. We report the results obtained for word and morpheme language models using medium (

This paper describes an automated system for assigning quality scores to recorded call center conversations. The system combines speech recognition, pattern matching, and maximum entropy classification to rank calls according to their measured quality. Calls at both end of the spectrum are flagged as "interesting" and made available for further human monitoring. In this process, pattern matching on the ASR transcript is used to answer a set of standard quality control questions such as "did the agent use courteous words and phrases," and to generate a question-based score. This is interpolated with the probability of a call being "bad," as determined by maximum entropy operating on a set of ASR-derived features such as "maximum silence length" and the occurrence of selected n-gram word sequences. The system is trained on a set of calls with associated manual evaluation forms. We present precision and recall results from IBM's North American Help Desk indicating that for a given amount of listening effort, this system triples the number of bad calls that are identified, over the current policy of randomly sampling calls

This paper describes an automated system for assigning quality scores to recorded call center conversations. The system combines speech recognition, pattern matching, and maximum entropy classification to rank calls according to their measured quality. Calls at both ends of the spectrum are flagged as "interesting" and made available for further human monitoring. In this process, the ASR transcript is used to answer a set of standard quality control questions such as "did the agent use courteous words and phrases," and to generate a question-based score. This is interpolated with the probability of a call being "bad," as determined by maximum entropy operating on a set of ASR-derived features such as "maximum silence length" and the occurrence of selected n-gram word sequences. The system is trained on a set of calls with associated manual evaluation forms. We present precision and recall results from IBM's North American Help Desk indicating that for a given amount of listening effort, this system triples the number of bad calls that are identified, over the current policy of randomly sampling calls. The application that will be demonstrated is a research prototype that was built in conjunction with IBM's North American call centers.

We describe the IBM systems submitted to the NIST RT06s Speech-to-Text (STT) evaluation campaign on the CHIL lecture meeting data for three conditions: Multiple distant microphone (MDM), single distant microphone (SDM), and individual headset microphone (IHM). The system building process is similar to the IBM conversational telephone speech recognition system. However, the best models for the far-field conditions (SDM and MDM) proved to be the ones that use neither variance normalization nor vocal tract length normalization. Instead, feature-space minimum-phone error discriminative training yielded the best results. Due to the relatively small amount of CHIL-domain data, the acoustic models of our systems are built on publicly available meeting corpora, with maximum a-posteriori adaptation applied twice on CHIL data during training: First, at the initial speaker-independent model, and subsequently at the minimum phone error model. For language modeling, we utilized meeting transcripts, text from scientific conference proceedings, and spontaneous telephone conversations. On development data, chosen in our work to be the 2005 CHIL-internal STT evaluation test set, the resulting language model provided a 4% absolute gain in word error rate (WER), compared to the model used in last year's CHIL evaluation. Furthermore, the developed STT system significantly outperformed our last year's results, by reducing close-talking microphone data WER from 36.9% to 25.4% on our development set. In the NIST RT06s evaluation campaign, both MDM and SDM systems scored well, however the IHM system did poorly due to unsuccessful cross-talk removal.

fMPE is a recently introduced discriminative training technique that uses the Minimum Phone Error (MPE) discriminative criterion to train a feature-level transformation. In this paper we investigate fMPE trained audio/visual features for multistream HMM-based audio-visual speech recognition. A flexible, layer-based implementation of fMPE allows us to combine the the visual information with the audio stream using the discriminative traning process, and dispense with the multiple stream approach. Experiments are reported on the IBM infrared headset audio-visual database. On average of 20-speaker 1 hour speaker independent test data, the fMPE trained acoustic features achieve 33% relative gain. Adding video layers on top of audio layers gives additional 10% gain over fMPE trained features from the audio stream alone. The fMPE trained visual features achieve 14% relative gain, while the decision fusion of audio/visual streams with fMPE trained features achieves 29% relative gain. However, fMPE trained models do not improve over the original models on the mismatched noisy test data.

We propose a non-linear feature space transformation for speaker/environment adaptation which forces the individual dimensions of the acoustic data for every speaker to be Gaussian distributed. The transformation is given by the preimage under the Gaussian cumulative distribution function (CDF) of the empirical CDF on a per dimension basis. We show that, for a given dimension, this transformation achieves minimum divergence between the density function of the transformed adaptation data and the normal density with zero mean and unit variance. Experimental results on both small and large vocabulary tasks show consistent improvements over the application of linear adaptation transforms only.

In this paper we report the use of discriminative training and other techniques to improve performance in a HMM-based isolated handwritten character recognition system. The discriminative training is maximum mutual information (MMI) training; we also improve results by using composite images which are the concatenation of the raw images, rotated and polar transformed versions of them; and we describe a technique called block-based principal component analysis (PCA). For effective discriminative training we need to increase the size of our training database, which we do by eroding and dilating the images to give a three-fold increase in training data. Although these techniques are tested using isolated Thai characters, both MMI and block-based PCA are applicable to the more difficult task of cursive handwriting recognition.

In this paper we show how a discriminative objective function such as Maximum Mutual Information (MMI) can be combined with a prior distribution over the HMM parameters to give a discriminative Maximum A Posteriori (MAP) estimate for HMM training. The prior distribution can be based around the Maximum Likelihood (ML) parameter estimates, leading to a technique previously referred to as I-smoothing; or for adaptation it can be based around a MAP estimate of the ML parameters, leading to what we call MMI-MAP. This latter approach is shown to be effective for task adaptation, where data from one task (Voicemail) is used to adapt a HMM set trained on another task (Switchboard). It is shown that MMI-MAP results in a 2.1% absolute reduction in word error rate relative to standard ML-MAP with 30 hours of Voicemail task adaptation data starting from a MMI-trained Switchboard system.

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 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.