Related papers: Just ASK: Building an Architecture for Extensible …
Developing decision-support systems that complement human performance in classification tasks remains an open challenge. A popular approach, Learning to Defer (LtD), allows a Machine Learning (ML) model to pass difficult cases to a human…
We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language…
Smart Home Assistants (SHAs) have become ubiquitous in modern households, offering convenience and efficiency through its voice interface. However, for Deaf and Hard-of-Hearing (DHH) individuals, the reliance on auditory and textual…
We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind. We discuss SSL for AMs in a small…
The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…
In this paper, we propose to improve end-to-end (E2E) spoken language understand (SLU) in an RNN transducer model (RNN-T) by incorporating a joint self-conditioned CTC automatic speech recognition (ASR) objective. Our proposed model is akin…
Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especially important in open-domain question answering, where broad or copied queries often…
Computer-assisted language learning -- CALL -- is an established research field. We review how artificial intelligence can be applied to support language learning and teaching. The need for intelligent agents that assist language learners…
Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…
Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…
In traditional (desktop) e-commerce search, a customer issues a specific query and the system returns a ranked list of products in order of relevance to the query. An increasingly popular alternative in e-commerce search is to issue a…
This article presents the design and the implementation of a cloud system for knowledge-based autonomous interaction devised for Social Robots and other conversational agents. The system is particularly convenient for low-cost robots and…
Spoken conversational agents are converging toward voice-native LLMs. This tutorial distills the path from cascaded ASR/NLU to end-to-end, retrieval-and vision-grounded systems. We frame adaptation of text LLMs to audio, cross-modal…
Recent advances in voice synthesis, coupled with the ease with which speech can be harvested for millions of people, introduce new threats to applications that are enabled by devices such as voice assistants (e.g., Amazon Alexa, Google Home…
Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question…
Building Agent Assistants that can help improve customer service support requires inputs from industry users and their customers, as well as knowledge about state-of-the-art Natural Language Processing (NLP) technology. We combine expertise…
Virtual assistants are becoming increasingly important speech-driven Information Retrieval platforms that assist users with various tasks. We discuss open problems and challenges with respect to modeling spoken information queries for…
The adoption of voice assistants like Alexa or Siri has grown rapidly, allowing users to instantly access information via voice search. Query suggestion is a standard feature of screen-based search experiences, allowing users to explore…
Millions of people take surveys every day, from market polls and academic studies to medical questionnaires and customer feedback forms. These datasets capture valuable insights, but their scale and structure present a unique challenge for…
Large Language Models (LLMs) have shown much promise in powering a variety of software engineering (SE) tools. Offering natural language as an intuitive interaction mechanism, LLMs have recently been employed as conversational ``programming…