Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

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

Digital processing of speech signals

An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

This paper introduces a new open source platform for end-to-end speech processing named ESPnet. ESPnet mainly focuses on end-to-end automatic speech recognition (ASR), and adopts widely-used dynamic neural network toolkits, Chainer and PyTorch, as a main deep learning engine. ESPnet also follows the Kaldi ASR toolkit style for data processing, feature extraction/format, and recipes to provide a complete setup for speech recognition and other speech processing experiments. This paper explains a major architecture of this software platform, several important functionalities, which differentiate ESPnet from other open source ASR toolkits, and experimental results with major ASR benchmarks.

ESPNet: End-to-end speech processing toolkit

We propose improved Deep Neural Network (DNN) training loss functions for more accurate single keyword spotting on resource-constrained embedded devices. The loss function modifications consist of a combination of multi-task training and weighted cross entropy. In the multi-task architecture, the keyword DNN acoustic model is trained with two tasks in parallel the main task of predicting the keyword-specific phone states, and an auxiliary task of predicting LVCSR senones. We show that multi-task learning leads to comparable accuracy over a previously proposed transfer learning approach where the keyword DNN training is initialized by an LVCSR DNN of the same input and hidden layer sizes. The combination of LVCSRinitialization and Multi-task training gives improved keyword detection accuracy compared to either technique alone. We also propose modifying the loss function to give a higher weight on input frames corresponding to keyword phone targets, with a motivation to balance the keyword and background training data. We show that weighted cross-entropy results in additional accuracy improvements. Finally, we show that the combination of 3 techniques LVCSR-initialization, multi-task training and weighted cross-entropy gives the best results, with significantly lower False Alarm Rate than the LVCSR-initialization technique alone, across a wide range of Miss Rates.

/pdf/multi-task-learning-and-weighted-cross-entropy-for-dnn-based-3fu4ca6c61.pdf

Multi-task learning and Weighted Cross-entropy for DNN-based Keyword Spotting

Techniques for determining when to perform an action associated with a voice command and when to disregard the voice command. In some instances, the techniques reference an identity of a user that utters a command when making this determination. For instance, if a first user awakens a device or initially begins providing voice commands to the device, the device or another computing device may perform actions associated with subsequent voice commands uttered by the same user, while disregarding voice commands from other users. That is, because the device is engaging in a dialog with a first user, the device may refrain from engaging in a dialog with a different user. Additionally or alternatively, the device may begin a new dialog with the different user, either upon identifying the command of the other user or upon finishing the dialog with the first user.

Accepting voice commands based on user identity

Once a popular theme of futuristic science fiction or far-fetched technology forecasts, digital home assistants with a spoken language interface have become a ubiquitous commodity today. This success has been made possible by major advancements in signal processing and machine learning for so-called far-field speech recognition, where the commands are spoken at a distance from the sound-capturing device. The challenges encountered are quite unique and different from many other use cases of automatic speech recognition (ASR). The purpose of this article is to describe, in a way that is amenable to the nonspecialist, the key speech processing algorithms that enable reliable, fully hands-free speech interaction with digital home assistants. These technologies include multichannel acoustic echo cancellation (MAEC), microphone array processing and dereverberation techniques for signal enhancement, reliable wake-up word and end-of-interaction detection, and high-quality speech synthesis as well as sophisticated statistical models for speech and language, learned from large amounts of heterogeneous training data. In all of these fields, deep learning (DL) has played a critical role.

/pdf/speech-processing-for-digital-home-assistants-combining-e0th85mkrw.pdf

Speech Processing for Digital Home Assistants: Combining signal processing with deep-learning techniques

We announce the public availability of the RWTH Aachen University speech recognition toolkit. The toolkit includes state of the art speech recognition technology for acoustic model training and decoding. Speaker adaptation, speaker adaptive training, unsupervised training, a finite state automata library, and an efficient tree search decoder are notable components. Comprehensive documentation, example setups for training and recognition, and a tutorial are provided to support newcomers.

/pdf/the-rwth-aachen-university-open-source-speech-recognition-v205z7unmn.pdf

The RWTH aachen university open source speech recognition system.

Features are disclosed for managing the use of speech recognition models and data in automated speech recognition systems. Models and data may be retrieved asynchronously and used as they are received or after an utterance is initially processed with more general or different models. Once received, the models and statistics can be cached. Statistics needed to update models and data may also be retrieved asynchronously so that it may be used to update the models and data as it becomes available. The updated models and data may be immediately used to re-process an utterance, or saved for use in processing subsequently received utterances. User interactions with the automated speech recognition system may be tracked in order to predict when a user is likely to utilize the system. Models and data may be pre-cached based on such predictions.

Bjorn Hoffmeister

Papers

Multi-task learning and Weighted Cross-entropy for DNN-based Keyword Spotting

Accepting voice commands based on user identity

Speech Processing for Digital Home Assistants: Combining signal processing with deep-learning techniques

The RWTH aachen university open source speech recognition system.

Speech model retrieval in distributed speech recognition systems