AIConfPaper
← Search

Spyros Matsoukas

7 accepted papers

2023

Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs

Abishek Komma, Nagesh Panyam Chandrasekarasastry, Timothy Leffel, Anuj Goyal, Angeliki Metallinou, Spyros Matsoukas +1
ACL 2023industry

Measurement of interaction quality is a critical task for the improvement of large-scale spoken dialog systems. Existing approaches to dialog quality estimation either focus on evaluating the quality of individual turns, or collect dialog-level quality measurements from end users immediately followi…

Cited by 3Source ↗PDF ↗Scholar ↗
2022

Federated Self-Supervised Learning for Acoustic Event Classification

Meng Feng, Chieh-Chi Kao, Qingming Tang, Ming Sun, Viktor Rozgic, Spyros Matsoukas +1
ICASSP 2022accepted

Standard acoustic event classification (AEC) solutions require large-scale collection of data from client devices for model optimization. Federated learning (FL) is a compelling frame- work that decouples data collection and model training to enhance customer privacy. In this work, we investigate th…

Cited by 14Source ↗Scholar ↗
2021

A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI Systems

Sunghyun Park, Han Li, Ameen Patel, Sidharth Mudgal, Sungjin Lee, Young-Bum Kim +2
EMNLP 2021main

Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request. We propose a scalable and automatic approach for improving NLU in a large-scale conversational AI sys…

Cited by 21Source ↗PDF ↗Scholar ↗
2021

Contrastive Unsupervised Learning for Speech Emotion Recognition

Mao Li, Bo Yang, Joshua Levy, Andreas Stolcke, Viktor Rozgic, Spyros Matsoukas +3
ICASSP 2021accepted

Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication. However, SER has long suffered from a lack of public large-scale labeled datasets. To circumvent this problem, we investigate how unsupervised representation learning on unlabeled datasets can be…

Cited by 0Source ↗Scholar ↗
2020

Few-Shot Acoustic Event Detection Via Meta Learning

Bowen Shi, Ming Sun, Krishna C. Puvvada, Chieh-Chi Kao, Spyros Matsoukas, Chao Wang
ICASSP 2020accepted

We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data. Compared to other research areas like computer vision, few-shot learning for audio recognition has been under-studied. We formulate few-shot AED problem a…

Cited by 0Source ↗Scholar ↗
2020

Towards Data-Efficient Modeling for Wake Word Spotting

Yixin Gao, Yuriy Mishchenko, Anish Shah, Spyros Matsoukas, Shiv Vitaladevuni
ICASSP 2020accepted

Wake word (WW) spotting is challenging in far-field not only because of the interference in signal transmission but also the complexity in acoustic environment. Traditional WW model training requires large amount of in-domain WW-specific data with substantial human annotations. This prevents the mod…

Cited by 0Source ↗Scholar ↗
2019

Semi-supervised Acoustic Event Detection Based on Tri-training

Bowen Shi, Ming Sun, Chieh-Chi Kao, Viktor Rozgic, Spyros Matsoukas, Chao Wang
ICASSP 2019accepted

This paper presents our work of training acoustic event detection (AED) models using unlabeled dataset. Recent acoustic event detectors are based on large-scale neural networks, which are typically trained with huge amounts of labeled data. Labels for acoustic events are expensive to obtain, and rel…

Cited by 0Source ↗Scholar ↗