Apple at Interspeech 2019
September 2019
Apple is attending Interspeech 2019, the world’s largest conference on the science and technology of spoken language processing. The conference, of which Apple is a Platinum Sponsor, will take place in Graz, Austria from September 15th to 19th. For Interspeech attendees, join the authors of our accepted papers at our booth to learn more about the great speech research happening at Apple.
Apple continues to build cutting-edge technology in the space of machine hearing, speech recognition, natural language processing, machine translation, text-to-speech, and artificial intelligence, improving the lives of millions of customers every day. If you’re interested in opportunities to make an impact on Apple products through machine learning research and development, check out our teams at Jobs at Apple.
Language Identification from Very Short Strings
Vol. 1, Issue 14 ∙ July 2019 by Input & Intelligence — Natural Language Processing Team
Many language-related tasks, such as entering text on your iPhone, discovering news articles you might enjoy, or finding out answers to questions you may have, are powered by language-specific natural language processing (NLP) models. To decide which model to invoke at a particular point in time, we must perform language identification (LID), often on the basis of limited evidence, namely a short character string. Performing reliable LID is more critical than ever as multi-lingual input is becoming more and more common across all Apple platforms. In most writing scripts — like Latin and Cyrillic, but also including Hanzi, Arabic, and others — strings composed of a few characters are often present in more than one language, making reliable identification challenging. In this article, we explore how we can improve LID accuracy by treating it as a sequence labeling problem at the character level, and using bi-directional long short-term memory (bi-LSTM) neural networks trained on short character sequences. We observed reductions in error rates varying from 15% to 60%, depending on the language, while achieving reductions in model size between 40% and 80% compared to previously shipping solutions. Thus the LSTM LID approach helped us identify language more correctly in features such as QuickType keyboards and Smart Responses, thereby leading to better auto-corrections, completions, and predictions, and ultimately a more satisfying user experience. It also made public APIs like the Natural Language framework more robust to multi-lingual environments.
View the article "Language Identification from Very Short Strings"
Bridging the Domain Gap for Neural Models
Vol. 1, Issue 13 ∙ June 2019
Deep neural networks are a milestone technique in the advancement of modern machine perception systems. However, in spite of the exceptional learning capacity and improved generalizability, these neural models still suffer from poor transferability. This is the challenge of domain shift—a shift in the relationship between data collected across different domains (e.g., computer generated vs. captured by real cameras). Models trained on data collected in one domain generally have poor accuracy on other domains. In this article, we discuss a new domain adaptation process that takes advantage of task-specific decision boundaries and the Wasserstein metric to bridge the domain gap, allowing the effective transfer of knowledge from one domain to another. As an additional advantage, this process is completely unsupervised, i.e., there is no need for new domain data to have labels or annotations.
View the article "Bridging the Domain Gap for Neural Models"
Optimizing Siri on HomePod in Far‑Field Settings
Vol. 1, Issue 12 ∙ December 2018 by Audio Software Engineering and Siri Speech Team
The typical audio environment for HomePod has many challenges — echo, reverberation, and noise. Unlike Siri on iPhone, which operates close to the user’s mouth, Siri on HomePod must work well in a far-field setting. Users want to invoke Siri from many locations, like the couch or the kitchen, without regard to where HomePod sits. A complete online system, which addresses all of the environmental issues that HomePod can experience, requires a tight integration of various multichannel signal processing technologies. Accordingly, the Audio Software Engineering and Siri Speech teams built a system that integrates both supervised deep learning models and unsupervised online learning algorithms and that leverages multiple microphone signals. The system selects the optimal audio stream for the speech recognizer by using top-down knowledge from the “Hey Siri” trigger phrase detectors. In this article, we discuss the machine learning techniques we use for online signal processing, as well as the challenges we faced and our solutions for achieving environmental and algorithmic robustness while ensuring energy efficiency.
View the article "Optimizing Siri on HomePod in Far‑Field Settings"
Apple at NeurIPS 2018
November 2018
This December we’ll be in Montreal, Canada, attending the 32nd Conference on Neural Information Processing Systems (NeurIPS). We’ll have a booth staffed with Machine Learning experts from across Apple who would love to chat with you. Please drop by if you’re attending the conference.
Apple is dedicated to advancing state-of-the-art machine learning technologies. As part of this, we’re building a team of exceptional researchers and engineers who can infuse intelligence into our devices and services to touch the lives of millions of users every day. We’re looking for people with backgrounds in various areas of machine learning. If you are interested in applying to specific machine learning positions, please explore opportunities at Machine Learning Jobs At Apple.
Can Global Semantic Context Improve Neural Language Models?
Vol. 1, Issue 11 ∙ September 2018 by Frameworks Natural Language Processing Team
Entering text on your iPhone, discovering news articles you might enjoy, finding out answers to questions you may have, and many other language-related tasks depend upon robust natural language processing (NLP) models. Word embeddings are a category of NLP models that mathematically map words to numerical vectors. This capability makes it fairly straightforward to find numerically similar vectors or vector clusters, then reverse the mapping to get relevant linguistic information. Such models are at the heart of familiar apps like News, search, Siri, keyboards, and Maps. In this article, we explore whether we can improve word predictions for the QuickType keyboard using global semantic context.
View the article "Can Global Semantic Context Improve Neural Language Models?"
Finding Local Destinations with Siri’s Regionally Specific Language Models for Speech Recognition
Vol. 1, Issue 10 ∙ August 2018 by Siri Speech Recognition Team
The accuracy of automatic speech recognition (ASR) systems has improved phenomenally over recent years, due to the widespread adoption of deep learning techniques. Performance improvements have, however, mainly been made in the recognition of general speech; whereas accurately recognizing named entities, like small local businesses, has remained a performance bottleneck. This article describes how we met that challenge, improving Siri’s ability to recognize names of local POIs by incorporating knowledge of the user’s location into our speech recognition system. Customized language models that take the user’s location into account are known as geolocation-based language models (Geo-LMs). These models enable Siri to better estimate the user’s intended sequence of words by using not only the information provided by the acoustic model and a general LM (like in standard ASR) but also information about the POIs in the user’s surroundings.
Personalized Hey Siri
Vol. 1, Issue 9 ∙ April 2018 by Siri Team
Apple introduced the “Hey Siri” feature with the iPhone 6 (iOS 8). This feature allows users to invoke Siri without having to press the home button. When a user says, “Hey Siri, how is the weather today?” the phone wakes up upon hearing “Hey Siri” and processes the rest of the utterance as a Siri request. The feature’s ability to listen continuously for the “Hey Siri” trigger phrase lets users access Siri in situations where their hands might be otherwise occupied, such as while driving or cooking, as well as in situations when their respective devices are not within arm’s reach. Imagine a scenario where a user is asking his or her iPhone 6 on the kitchen counter to set a timer while putting a turkey into the oven.
Learning with Privacy at Scale
Vol. 1, Issue 8 ∙ December 2017 by Differential Privacy Team
Understanding how people use their devices often helps in improving the user experience. However, accessing the data that provides such insights — for example, what users type on their keyboards and the websites they visit — can compromise user privacy. We develop a system architecture that enables learning at scale by leveraging local differential privacy, combined with existing privacy best practices. We design efficient and scalable local differentially private algorithms and provide rigorous analyses to demonstrate the tradeoffs among utility, privacy, server computation, and device bandwidth. Understanding the balance among these factors leads us to a successful practical deployment using local differential privacy. This deployment scales to hundreds of millions of users across a variety of use cases, such as identifying popular emojis, popular health data types, and media playback preferences in Safari.
An On-device Deep Neural Network for Face Detection
Vol. 1, Issue 7 ∙ November 2017 by Computer Vision Machine Learning Team
Apple started using deep learning for face detection in iOS 10. With the release of the Vision framework, developers can now use this technology and many other computer vision algorithms in their apps. We faced significant challenges in developing the framework so that we could preserve user privacy and run efficiently on-device. This article discusses these challenges and describes the face detection algorithm.
View the article "An On-device Deep Neural Network for Face Detection"
Hey Siri: An On-device DNN-powered Voice Trigger for Apple’s Personal Assistant
Vol. 1, Issue 6 ∙ October 2017 by Siri Team
The “Hey Siri” feature allows users to invoke Siri hands-free. A very small speech recognizer runs all the time and listens for just those two words. When it detects “Hey Siri”, the rest of Siri parses the following speech as a command or query. The “Hey Siri” detector uses a Deep Neural Network (DNN) to convert the acoustic pattern of your voice at each instant into a probability distribution over speech sounds. It then uses a temporal integration process to compute a confidence score that the phrase you uttered was “Hey Siri”. If the score is high enough, Siri wakes up. This article takes a look at the underlying technology. It is aimed primarily at readers who know something of machine learning but less about speech recognition.
View the article "Hey Siri: An On-device DNN-powered Voice Trigger for Apple’s Personal Assistant"
Real-Time Recognition of Handwritten Chinese Characters Spanning a Large Inventory of 30,000 Characters
Vol. 1, Issue 5 ∙ September 2017 by Handwriting Recognition Team
Handwriting recognition is more important than ever given the prevalence of mobile phones, tablets, and wearable gear like smartwatches. The large symbol inventory required to support Chinese handwriting recognition on such mobile devices poses unique challenges. This article describes how we met those challenges to achieve real-time performance on iPhone, iPad, and Apple Watch (in Scribble mode). Our recognition system, based on deep learning, accurately handles a set of up to 30,000 characters. To achieve acceptable accuracy, we paid particular attention to data collection conditions, representativeness of writing styles, and training regimen. We found that, with proper care, even larger inventories are within reach. Our experiments show that accuracy only degrades slowly as the inventory increases, as long as we use training data of sufficient quality and in sufficient quantity.
Deep Learning for Siri’s Voice: On-device Deep Mixture Density Networks for Hybrid Unit Selection Synthesis
Vol. 1, Issue 4 ∙ August 2017 by Siri Team
Siri is a personal assistant that communicates using speech synthesis. Starting in iOS 10 and continuing with new features in iOS 11, we base Siri voices on deep learning. The resulting voices are more natural, smoother, and allow Siri’s personality to shine through. This article presents more details about the deep learning based technology behind Siri’s voice.
Inverse Text Normalization as a Labeling Problem
Vol. 1, Issue 3 ∙ August 2017 by Siri Team
Siri displays entities like dates, times, addresses and currency amounts in a nicely formatted way. This is the result of the application of a process called inverse text normalization (ITN) to the output of a core speech recognition component. To understand the important role ITN plays, consider that, without it, Siri would display “October twenty third twenty sixteen” instead of “October 23, 2016”. In this work, we show that ITN can be formulated as a labelling problem, allowing for the application of a statistical model that is relatively simple, compact, fast to train, and fast to apply. We demonstrate that this approach represents a practical path to a data-driven ITN system.
View the article "Inverse Text Normalization as a Labeling Problem"
Improving Neural Network Acoustic Models by Cross-bandwidth and Cross-lingual Initialization
Vol. 1, Issue 2 ∙ August 2017 by Siri Team
Users expect Siri speech recognition to work well regardless of language, device, acoustic environment, or communication channel bandwidth. Like many other supervised machine learning tasks, achieving such high accuracy usually requires large amounts of labeled data. Whenever we launch Siri in a new language, or extend support to different audio channel bandwidths, we face the challenge of having enough data to train our acoustic models. In this article, we discuss transfer learning techniques that leverage data from acoustic models already in production. We show that the representations are transferable not only across languages but also across audio channel bandwidths. As a case study, we focus on recognizing narrowband audio over 8 kHz Bluetooth headsets in new Siri languages. Our techniques help to improve significantly Siri’s accuracy on the day we introduce a new language.
Improving the Realism of Synthetic Images
Vol. 1, Issue 1 ∙ July 2017
Most successful examples of neural nets today are trained with supervision. However, to achieve high accuracy, the training sets need to be large, diverse, and accurately annotated, which is costly. An alternative to labelling huge amounts of data is to use synthetic images from a simulator. This is cheap as there is no labeling cost, but the synthetic images may not be realistic enough, resulting in poor generalization on real test images. To help close this performance gap, we’ve developed a method for refining synthetic images to make them look more realistic. We show that training models on these refined images leads to significant improvements in accuracy on various machine learning tasks.
View the article "Improving the Realism of Synthetic Images"
Welcome
July 2017
Welcome to the Apple Machine Learning Journal. Here, you can read posts written by Apple engineers about their work using machine learning technologies to help build innovative products for millions of people around the world. If you’re a machine learning researcher or student, an engineer or developer, we’d love to hear your questions and feedback. Write us at machine-learning@apple.com