Research Papers

title

authors

conference
/ journal

research areas

date

Generative Context-Aware Fine-Tuning of Self-Supervised Speech Models

AUTHORS

Suwon Shon

Kwangyoun Kim

Prashant Sridhar

Yi-Te Hsu

Shinji Watanabe

Karen Livescu

conference/journal

ICASSP 2024

RESEARCH AREAS

Computation and Language

‍Sound

Audio and Speech Processing

Date

Dec 2024

Sparse Rewards Can Self-Train Dialogue Agents

AUTHORS

Barrett Martin Lattimer

Varun Gangal

Ryan McDonald

Yi Yang

‍

conference/journal

ICLR2025

RESEARCH AREAS

Computation and Language

‍

Date

Sep 2024

Convolution-Augmented Parameter-Efficient Fine-Tuning for Speech Recognition

AUTHORS

Kwangyoun Kim

Suwon Shon

Yi-Te Hsu

Prashant Sridhar

Karen Livescu

Shinji Watanabe

‍

conference/journal

Interspeech 2024

RESEARCH AREAS

Date

Sep 2024

Sample-efficient diffusion for text-to-speech synthesis

AUTHORS

Justin Lovelace

Soham Ray

Kwangyoun Kim

Kilian Q. Weinberger

Felix Wu

‍

conference/journal

Interspeech 2024

RESEARCH AREAS

Sound

Artificial Intelligence

Machine Learning

‍

Date

Sep 2024

Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses

AUTHORS

Dongxu Zhang

Varun Gangal

Barrett Martin Lattimer

Yi Yang

‍

conference/journal

ACL 2024

RESEARCH AREAS

Artificial Intelligence

Computation and Language

‍

Date

Jul 2024

DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding

AUTHORS

Suwon Shon

Kwangyoun Kim

Yi-Te Hsu

Prashant Sridhar

Shinji Watanabe

Karen Livescu

‍

conference/journal

Interspeech 2024

RESEARCH AREAS

Computation and Language

Sound

Audio and Speech Processing

‍

Date

Jun 2024

Call Translator with Voice Cloning Using Transformers

AUTHORS

Nawaz Fateen Khan

Nandan Hemanth

Navyae Goyal

Pranav KR

Pooja Agarwal

‍

conference/journal

IEEE 2024

RESEARCH AREAS

Machine learning algorithms
Navigation
Cloning
Speech recognition
Machine learning
Linguistics
Transformers

‍

Date

Jun 2024

SteP: Stacked LLM Policies for Web Actions

AUTHORS

Paloma_Sodhi

S.R.K Branavan

Yoav Artzi

Ryan McDonald

‍

conference/journal

COLM 2024

RESEARCH AREAS

LMs with tools and code

Date

May 2024

Improving ASR Contextual Biasing with Guided Attention

AUTHORS

Jiyang Tang

‍Kwangyoun Kim

‍Suwon Shon

‍Felix Wu

‍Prashant Sridhar

Shinji Watanabe

conference/journal

ICASSP 2024

RESEARCH AREAS

Computation and Language

‍Audio and Speech Processing

Date

Jan 2024

Fast and Accurate Factual Inconsistency Detection Over Long Documents

AUTHORS

Barrett Martin Lattimer

Patrick Chen

Xinyuan Zhang

Yi Yang

conference/journal

EMNLP 2023

RESEARCH AREAS

Hallucination Detection

Dialogue Evaluation

Language Models

Date

Dec 2023

title

PATENT NUMBER

LINK

Few Shot Named Entity Recognition

PATENT NUMBER

11,860,684

Link

View Details

Predicting Customer Support Requests

PATENT NUMBER

11,790,376

Link

View Details

Flexible Capacity in an Electronic Environment

PATENT NUMBER

11,790,375

Link

View Details

System, Method, and Computer Program for Extracting Utterances Corresponding to a User Problem Statement in a Conversation Between a Human Agent and a User

PATENT NUMBER

11,763,803

Link

View Details

Trend Detection Via Machine Learning Models

PATENT NUMBER

11,763,230

Link

View Details

Automated Conversation Goal Discovery Using Neural Networks and Deep Multi-View Clustering

PATENT NUMBER

11,687,730

Link

View Details

Clarification of Natural Language Requests Using Neural Networks

PATENT NUMBER

11,610,064

Link

View Details

Modifying Text According to a Specified Attribute

PATENT NUMBER

11,610,061

Link

View Details

Mathematical Models of Graphical User Interfaces

PATENT NUMBER

11,567,851

Link

View Details

Initialization of Automated Workflows

PATENT NUMBER

11,588,760

Link

View Details

Automated Communications Over Multiple Channels

PATENT NUMBER

11,588,759

Link

View Details

Intent Discovery with a Prototype Classifier

PATENT NUMBER

11,551,004

Link

View Details

Adapting Application Programming Interfaces with Schema Mappings

PATENT NUMBER

11,537,448

Link

View Details

Speech Sentiment Analysis Using a Speech Sentiment Classifier Pretrained with Pseudo Sentiment Labels

PATENT NUMBER

11,521,639

Link

View Details

System, Method, and Computer Program for Obtaining a Unified Named Entity Recognition Model with the Collective Predictive Capabilities of Teacher Models with Different Tag Sets Using Marginal Distillation

PATENT NUMBER

11,487,944

Link

View Details

Customized Message Suggestion With User Embedding Vectors

PATENT NUMBER

11,425,064

Link

View Details

Removing Personal Information From Text Using Multiple Levels of Redaction

PATENT NUMBER

11,386,259

Link

View Details

Maintaining Machine Language Model State Across Communication Channels

PATENT NUMBER

11,373,044

Link

View Details

Automatic Software Generation For Computer Systems

PATENT NUMBER

11,262,986

Link

View Details

File Matching With Rationale Alignment Using Neural Networks And An Optimal Transport Algorithm

PATENT NUMBER

11,238,278

Link

View Details

Processing An Incomplete Message With A Neural Network To Generate Suggested Messages

PATENT NUMBER

11,216,510

Link

View Details

System, Method, and Computer Program for Creating a Complete Transcription of an Audio Recording from Separately Transcribed Redacted and Unredacted Words

PATENT NUMBER

11,138,970

Link

View Details

Fast Neural Network Implementations by Increasing Parallelism of Cell Computations

PATENT NUMBER

11,106,975

Link

View Details

Identifying Representative Conversations Using a State Model

PATENT NUMBER

10,984,781

Link

View Details

Automated Upsells in Customer Conversations

PATENT NUMBER

10,885,529

Link

View Details

Using a Neural Network to Optimize Processing of User Requests

PATENT NUMBER

10,762,423

Link

View Details

Processing Communications Using a Prototype Classifier

PATENT NUMBER

10,747,957

Link

View Details

Assisting Entities in Responding to a Request of a User

PATENT NUMBER

10,733,614

Link

View Details

Suggesting Resources Using Context Hashing

PATENT NUMBER

10,650,311

Link

View Details

Using Semantic Processing for Customer Support

PATENT NUMBER

10,535,071

Link

View Details

Updating Natural Language Interfaces by Processing Usage Data

PATENT NUMBER

10,515,104

Link

View Details

Automatic Communication Using an Intent Classifier

PATENT NUMBER

10,497,004

Link

View Details

Maintaining Quality of Customer Support Messages

PATENT NUMBER

10,489,792

Link

View Details

Word Hash Language Model

PATENT NUMBER

10,482,875

Link

View Details

Automatically Suggesting Resources for Responding to a Request

PATENT NUMBER

10,453,074

Link

View Details

Assisting Entities in Responding to a Request of a User

PATENT NUMBER

10,387,888

Link

View Details

Detecting Events from Customer Support Sessions

PATENT NUMBER

10,334,106

Link

View Details

Updating Natural Language Interfaces by Processing Usage Data

PATENT NUMBER

10,210,244

Link

View Details

Removing Personal Information from Text Using a Neural Network

PATENT NUMBER

10,169,315

Link

View Details

Word Hash Language Model

PATENT NUMBER

10,109,275

Link

View Details

Detecting Events from Customer Support Sessions

PATENT NUMBER

10,097,690

Link

View Details

Using Semantic Processing for Customer Support

PATENT NUMBER

10,083,451

Link

View Details

Method, Medium, and System for Responding to Customer Requests with State Tracking

PATENT NUMBER

9,892,414

Link

View Details

Automatically Suggesting Completions of Text

PATENT NUMBER

9,807,037

Link

View Details

Automatically Suggesting Response to a Received Message

PATENT NUMBER

9,805,371

Link

View Details

Automatically Responding to a Request of a User

PATENT NUMBER

9,715,496

Link

View Details

Automatic Calibration of Command-Detection Thresholds

PATENT NUMBER

8,990,079

Link

View Details

Method and Apparatus to Generate Audio Versions of Web Pages

PATENT NUMBER

8,838,673

Link

View Details

Process and System for the Semantic Selection of Document Templates

PATENT NUMBER

7,492,949

Link

View Details

Method for Producing a Speech Rendition of Text from Diphone Sounds

PATENT NUMBER

6,879,957

Link

View Details

Get Started

AI Services Value Calculator

Estimate your cost savings

Calculate Savings

Request a Demo

Get Started

Transform your enterprise with generative AI • Optimize and grow your CX •