Sara Berger

Slava Shechtman

Raul Fernandez

David Haws

Kim Martineau

Rachel Ostrand

Research

Converting several audio streams into one voice makes it easier for AI to learn

Training a customer service bot to sound more human

A cognitive in-car companion to help us enjoy the journey

Speech-to-text AI could help doctors prescribe placebo to ease chronic pain

Austin or Boston? Making artificial speech more expressive, natural, and controllable

The pandemic changed the way we understand speech

NeurIPS 2024

ICASSP 2025

NAACL 2025

Foundation Models

Machine Learning

Natural Language Processing

Generative AI

Speech

Science

Healthcare

Modern computing architectures are revolutionizing the way business gets done. We’re working on tools to help businesses automate much of their daily processes, to save time and drive new insights through trusted, safe, and explainable AI systems.

AI for Business Automation

For AI to be useful, it needs to understand what’s being asked of it, and to know how to respond. At IBM Research, we’re working on systems to help AI better reason with the tasks it’s presented, such as understanding context and analogies, comprehension, and planning through scenarios. 

Knowledge and Reasoning

Much of the information that can help transform enterprises is locked away in text, like documents, tables, and charts. We’re building advanced AI systems that can parse vast bodies of text to help unlock that data, but also ones flexible enough to be applied to any language problem.

As more of the world moves online, the demand for systems that can understand users and speak to them in natural language is growing exponentially. At IBM Research, we're working on next-generation AI that learns to decipher and replicate the way humans speak.

The demand for virtual agents that can handle customer needs has continued to increase dramatically. At IBM Research, we’re building the next generation of artificial intelligence systems that can understand what’s being asked of them and how best to respond as efficiently as possible.

Conversational AI

Speech

Our work

Training a customer service bot to sound more human

Converting several audio streams into one voice makes it easier for AI to learn

The pandemic changed the way we understand speech

Austin or Boston? Making artificial speech more expressive, natural, and controllable

Speech-to-text AI could help doctors prescribe placebo to ease chronic pain

A cognitive in-car companion to help us enjoy the journey

Publications

Comprehensive Layer-Wise Analysis of SSL Models for Audio Deepfake Detection

Knowledge Distillation Based Training of Unified Conformer CTC Models for Multi-form ASR

A Non-autoregressive Model for Joint STT and TTS

LLM based Text Generation for Improved Low-resource Speech Recognition Models

Beyond neuropsychological tests: AI speech analysis in PKU

Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models

Related topics