Amazon Science Blog

A central task of natural-language-understanding systems, like the ones that power Alexa, is domain classification, or determining the general subject of a user’s utterances. Voice services must make finer-grained determinations, too, such as the particular actions that a customer wants executed. But domain classification makes those determinations much more efficient, by narrowing the range of possible interpretations.

Echo devices have already attracted tens of millions of customers, but in the Alexa AI group, we’re constantly working to make Alexa’s speech recognition systems even more accurate.

Alexa’s ability to act on spoken requests depends on statistical models that translate speech to text and text to actions. Historically, the models’ decisions were one-size-fits-all: the same utterance would produce the same action, regardless of context.

To handle more-natural spoken interactions, Alexa must track references through several rounds of conversation. If, for instance, a customer says, “How far is it to Redmond?” and after the answer follows up by saying, “Find good Indian restaurants there”, Alexa should be able to infer that “there” refers to Redmond.

This year’s Interspeech — the largest conference in speech technology — will take place in Hyderabad, India, the first week of September. More than 40 Amazon researchers will be attending, including Björn Hoffmeister, the senior manager for machine learning in the Alexa Automatic Speech Recognition group. He took a few minutes to answer three questions about this year’s conference.

Here’s a fairly common interaction with Alexa: “Alexa, set volume to five”; “Alexa, play music”. Even though the queries come in quick succession, the customer needs to repeat the wake word “Alexa”. To allow for more natural interactions, the device could immediately re-enter its listening state after the first query, without wake-word repetition; but that would require it to detect whether a follow-up speech input is indeed a query intended for the device (“device-directed”) or just background speech (“non-device-directed”).

At the annual meeting of the North American chapter of the Association for Computational Linguistics in June, researchers at Amazon and the University of Sheffield released a new dataset that can be used to train machine-learning systems to determine the veracity of factual assertions online. The dataset is called FEVER, for fact extraction and verification.

"Perfect hashing" is among the techniques that reduce the memory footprints of machine learning models by 94%.

New machine-learned multilingual named-entity transliteration system.

Automatic speech recognition systems, which convert spoken words into text, are an important component of conversational agents such as Alexa. These systems generally comprise an acoustic model, a pronunciation model, and a statistical language model. The role of the statistical language model is to assign a probability to the next word in a sentence, given the previous ones. For instance, the phrases “Pulitzer Prize” and “pullet surprise” may have very similar acoustic profiles, but statistically, one is far more likely to conclude a question that begins “Alexa, what playwright just won a … ?”

To be as useful as possible to customers, Alexa should be able to make educated guesses about the meanings of ambiguous utterances. If, for instance, a customer says, “Alexa, play the song ‘Hello’”, Alexa should be able to infer from the customer’s listening history whether the song requested is the one by Adele or the one by Lionel Richie.

In June 2018, Amazon announced the 11 focus areas of the 2018 Amazon Research Awards.

Amazon Alexa currently has more than 40,000 third-party skills, which customers use to get information, perform tasks, play games, and more. To make it easier for customers to find and engage with skills, we are moving toward skill invocation that doesn’t require mentioning a skill by name (as highlighted in a recent post).