Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input. An alternative way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition benchmarks, sometimes by a large margin. This article provides an overview of this progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state automata (using the freely available OpenFst), together with detailed documentation and a comprehensive set of scripts for building complete recognition systems. Kaldi is written is C++, and the core library supports modeling of arbitrary phonetic-context sizes, acoustic modeling with subspace Gaussian mixture models (SGMM) as well as standard Gaussian mixture models, together with all commonly used linear and affine transforms. Kaldi is released under the Apache License v2.0, which is highly nonrestrictive, making it suitable for a wide community of users.

/pdf/the-kaldi-speech-recognition-toolkit-3g790z933t.pdf

The Kaldi Speech Recognition Toolkit

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.

/pdf/librispeech-an-asr-corpus-based-on-public-domain-audio-books-gslbn35u4y.pdf

Librispeech: An ASR corpus based on public domain audio books

Recent advances in convolutional neural networks

We propose a novel context-dependent (CD) model for large-vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output. The deep belief network pre-training algorithm is a robust and often helpful way to initialize deep neural networks generatively that can aid in optimization and reduce generalization error. We illustrate the key components of our model, describe the procedure for applying CD-DNN-HMMs to LVSR, and analyze the effects of various modeling choices on performance. Experiments on a challenging business search dataset demonstrate that CD-DNN-HMMs can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs, with an absolute sentence accuracy improvement of 5.8% and 9.2% (or relative error reduction of 16.0% and 23.2%) over the CD-GMM-HMMs trained using the minimum phone error rate (MPE) and maximum-likelihood (ML) criteria, respectively.

/pdf/context-dependent-pre-trained-deep-neural-networks-for-large-14o17jhkzd.pdf

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

We propose to adapt deep neural network (DNN) acoustic models to a target speaker by supplying speaker identity vectors (i-vectors) as input features to the network in parallel with the regular acoustic features for ASR. For both training and test, the i-vector for a given speaker is concatenated to every frame belonging to that speaker and changes across different speakers. Experimental results on a Switchboard 300 hours corpus show that DNNs trained on speaker independent features and i-vectors achieve a 10% relative improvement in word error rate (WER) over networks trained on speaker independent features only. These networks are comparable in performance to DNNs trained on speaker-adapted features (with VTLN and FMLLR) with the advantage that only one decoding pass is needed. Furthermore, networks trained on speaker-adapted features and i-vectors achieve a 5-6% relative improvement in WER after hessian-free sequence training over networks trained on speaker-adapted features only.

Speaker adaptation of neural network acoustic models using i-vectors

Deep Convolutional Neural Networks for Large-scale Speech Tasks

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.

Boosted MMI for model and feature-space discriminative training

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.

/pdf/fmpe-discriminatively-trained-features-for-speech-3ltyy4j430.pdf

fMPE: discriminatively trained features for speech recognition

One of the most difficult speech recognition tasks is accurate recognition of human to human communication. Advances in deep learning over the last few years have produced major speech recognition improvements on the representative Switchboard conversational corpus. Word error rates that just a few years ago were 14% have dropped to 8.0%, then 6.6% and most recently 5.8%, and are now believed to be within striking range of human performance. This then raises two issues - what IS human performance, and how far down can we still drive speech recognition error rates? A recent paper by Microsoft suggests that we have already achieved human performance. In trying to verify this statement, we performed an independent set of human performance measurements on two conversational tasks and found that human performance may be considerably better than what was earlier reported, giving the community a significantly harder goal to achieve. We also report on our own efforts in this area, presenting a set of acoustic and language modeling techniques that lowered the word error rate of our own English conversational telephone LVCSR system to the level of 5.5%/10.3% on the Switchboard/CallHome subsets of the Hub5 2000 evaluation, which - at least at the writing of this paper - is a new performance milestone (albeit not at what we measure to be human performance!). On the acoustic side, we use a score fusion of three models: one LSTM with multiple feature inputs, a second LSTM trained with speaker-adversarial multi-task learning and a third residual net (ResNet) with 25 convolutional layers and time-dilated convolutions. On the language modeling side, we use word and character LSTMs and convolutional WaveNet-style language models.

George Saon

Papers

Speaker adaptation of neural network acoustic models using i-vectors

Deep Convolutional Neural Networks for Large-scale Speech Tasks

Boosted MMI for model and feature-space discriminative training

fMPE: discriminatively trained features for speech recognition

English Conversational Telephone Speech Recognition by Humans and Machines