Search results

Building socialbots that can have deep, engaging open-domain conversations with humans is one of the grand challenges of artificial intelligence (AI). To this end, bots need to be able to leverage world knowledge spanning several domains effectively when conversing with humans who have their own world knowledge. Existing knowledge-grounded conversation datasets are primarily stylized with explicit roles

Pre-trained models have demonstrated their effectiveness in many downstream natural language processing (NLP) tasks. The availability of multilingual pre-trained models enables zero-shot transfer of NLP tasks from high resource languages to low resource ones. However, recent research in improving pre-trained models focuses heavily on English. While it is possible to train the latest neural architectures

We present the results of the second Fact Extraction and VERification (FEVER2.0) Shared Task. The task challenged participants to both build systems to verify factoid claims using evidence retrieved from Wikipedia and to generate adversarial attacks against other participant’s systems. The shared task had three phases: building, breaking and fixing. There were 8 systems in the builder’s round, three of

A person’s tone of voice can tell you a lot about how they’re feeling. Not surprisingly, emotion recognition is an increasingly popular conversational-AI research topic.

Text normalization is an important process in conversational AI. If an Alexa customer says, “book me a table at 5:00 p.m.”, the automatic speech recognizer will transcribe the time as “five p m”. Before a skill can handle this request, “five p m” will need to be converted to “5:00PM”. Once Alexa has processed the request, it needs to synthesize the response — say, “Is 6:30 p.m. okay?” Here, 6:30PM will be converted to “six thirty p m” for the text-to-speech synthesizer. We call the process of converting “5:00PM” to “five p m” text normalization and its counterpart — converting “five p m” to “5:00PM” — inverse text normalization.

Recently, we published a paper showing that training a neural network to do language processing in English, then retraining it in German, drastically reduces the amount of German-language training data required to achieve a given level of performance.

Using cosine similarity rather than dot product to compare vectors helps prevent "catastrophic forgetting".

Traditionally, Alexa has interpreted customer requests according to their intents and slots. If you say, “Alexa, play ‘What’s Going On?’ by Marvin Gaye,” the intent should be PlayMusic, and “‘What’s Going On?’” and “Marvin Gaye” should fill the slots SongName and ArtistName.

When a customer asks Alexa to play “Hey Jude”, and Alexa responds, “Playing 'Hey Jude' by the Beatles,” that response is generated by a text-to-speech (TTS) system, which converts textual inputs into synthetic-speech outputs...

One of the ways that we’re always trying to improve Alexa’s performance is by teaching her to ignore speech that isn’t intended for her. At this year’s International Conference on Acoustics, Speech, and Signal Processing, my colleagues and I will present a new technique for doing this, which could complement the techniques that Alexa already uses.

Last year, Amazon announced the beta release of Alexa Guard, a new service that lets customers who are leaving the house instruct their Echo devices to listen for glass breaking or smoke and carbon dioxide alarms going off. At this year’s International Conference on Acoustics, Speech, and Signal Processing, our team is presenting several papers on sound detection. I wrote about one of them a few weeks ago, a new method for doing machine learning with unbalanced data sets.

Multiband dynamics processing, which separately modifies volume in different frequency bands of an audio signal, is known to improve listeners’ audio experiences. But in the context of voice-controlled systems like the Amazon Echo family of products, it can also improve automatic speech recognition by making echo cancellation easier.

Transfer learning is the technique of adapting a machine learning model trained on abundant data to a new context in which training data is sparse. On the Alexa team, we’ve explored transfer learning as a way to bootstrap new functions and to add new classification categories to existing machine learning systems.

Customer interactions with Alexa are constantly growing more complex, and on the Alexa science team, we strive to stay ahead of the curve by continuously improving Alexa’s speech recognition system. Increasingly, keeping pace with Alexa’s expanding capabilities will require automating the learning process, through techniques such as semi-supervised learning, which leverages a small amount of annotated data to extract information from a much larger store of unannotated data.

The idea of using arrays of microphones to improve automatic speech recognition (ASR) is decades old. The acoustic signal generated by a sound source reaches multiple microphones with different time delays. This information can be used to create virtual directivity, emphasizing a sound arriving from a direction of interest and diminishing signals coming from other directions. In voice recognition, one of the more popular methods for doing this is known as “beamforming”.

Audio watermarking is the process of adding a distinctive sound pattern — undetectable to the human ear — to an audio signal to make it identifiable to a computer. It’s one of the ways that video sites recognize copyrighted recordings that have been posted illegally. To identify a watermark, a computer usually converts a digital file into an audio signal, which it processes internally.

Sentiment analysis is the attempt, computationally, to determine from someone’s words how he or she feels about something. It has a host of applications, in market research, media analysis, customer service, and product recommendation, among other things. Sentiment classifiers are typically machine learning systems, and any given application of sentiment analysis may suffer from a lack of annotated data for training purposes.

Although deep neural networks have enabled accurate large-vocabulary speech recognition, training them requires thousands of hours of transcribed data, which is time-consuming and expensive to collect. So Amazon scientists have been investigating techniques that will let Alexa learn with minimal human involvement, techniques that fall in the categories of unsupervised and semi-supervised learning.

In experiments involving sound recognition, technique reduces error rate by 15% to 30%.

The 2018 Alexa Prize featured eight student teams from four countries, each of which adopted distinctive approaches to some of the central technical questions in conversational AI. We survey those approaches in a paper we released late last year, and the teams themselves go into even greater detail in the papers they submitted to the latest Alexa Prize Proceedings. Here, we touch on just a few of the teams’ innovations.