• Skip to primary navigation
  • Skip to main content
SRI logo
  • About
    • Press room
  • Expertise
    • Advanced imaging systems
    • Artificial intelligence
    • Biomedical R&D services
    • Biomedical sciences
    • Computer vision
    • Cyber & formal methods
    • Education and learning
    • Innovation strategy and policy
    • National security
    • Ocean & space
    • Quantum
    • QED-C
    • Robotics, sensors & devices
    • Speech & natural language
    • Video test & measurement
  • Ventures
  • NSIC
  • Careers
  • Contact
  • 日本支社
Search
Close

Speech & natural language

The human voice is a powerful tool. SRI’s speech and language technologies not only allow us to interact more naturally with computing applications—they also provide a wealth of actionable information about our intentions, health and emotional state.

CONTACT US

Core technologies and applications

SRI’s Speech Technology and Research (STAR) Laboratory brings together a multidisciplinary mix of engineers, computer scientists and linguists. Together our experts build systems for a wide range of applications including signal processing; data indexing and mining; and computer-aided learning.

Speech recognition

Noise robustness

Speech production and perception-based features

Keyword spotting

Prosodic modeling and disfluencies

Speech & audio analytics

Voice biometrics

Language/accent identification

Speaker and speaker-state characterization

Audio event detection

Speaker diarization

Machine translation

Speech-to-Speech translation

Cross-lingual information retrieval

Machine-mediated cross-lingual communication

Natural language understanding

Human-computer interaction

Dialog systems and virtual personal assistants (VPAs)

Error detection and recovery

Semantic and syntactic parsing

Information extraction

Multi-lingual information extraction

Topic and event identification

Summarization;

Question answering

Our work

more +

  • Nuance Partners with SCIENTIA Puerto Rico
    July 5, 2022

    Nuance Partners with SCIENTIA Puerto Rico

    SRI spin-out Nuance Communications to expand access its Dragon Medical One for the island’s physicians and nurses

  • Aaron Lawson talks about the STAR Lab at SRI
    November 16, 2021

    Aaron Lawson talks about the STAR Lab at SRI

    Aaron Lawson is Assistant Lab Director at SRI’s Speech Technology and Research (STAR) lab. STAR lab brings together a multidisciplinary mix of engineers, computer scientists and linguists. Together their experts build systems for a wide range of applications including signal processing; data indexing and mining; and computer-aided learning. Join us to learn about how STAR […]

  • Faking videos is easy, deep nostalgia shows
    March 5, 2021

    Faking videos is easy, deep nostalgia shows

    Lifewire features SRI’s STAR Lab in a discussion around AI and techniques powering deepfakes

Speech and Natural language leadership

william-mark-bio-pic

William Mark

President, Information and Computing Sciences

dimitra-vergyri-bio-pic

Dimitra Vergyri

Director, Speech Technology and Research Laboratory (STAR)

Featured researchers

dimitra-vergyri-bio-pic

Dimitra Vergyri

Director, Speech Technology and Research Laboratory (STAR)

horacio-franco-bio-pic

Horacio Franco

Chief Scientist, Speech Technology and Research Laboratory

Aaron Lawson

Assistant Laboratory Director, Speech Technology and Research Laboratory

martin-graciarena-bio-pic

Martin Graciarena

Technical Manager, Speech Technology and Research Laboratory

mitchell-mclaren-bio-pic

Mitchell McLaren

Senior Computer Scientist, Speech Technology and Research Laboratory

harry-bratt-bio-pic

Harry Bratt

Senior Computer Scientist, Speech Technology and Research Laboratory

Platforms

Open Language Interface for Voice Exploitation (OLIVE)

Novel speech processing technology leverages AI algorithms to enable speech activity detection in high levels of noise and distortion.

Learn more +

SenSay

Real-time speaker state platform estimates speaker state—such as emotion, sentiment, cognition, health, mental health and communication quality—in a range of end applications.

Learn more +

DynaSpeak® speech recognition engine

Small-footprint, high-accuracy engine incorporates patented techniques that increase recognition performance using speaker adaptation, microphone adaptation, end-of- speech detection, distributed speech recognition and noise robustness.

Learn more +

EduSpeak® speech recognition toolkit

Toolkit specifically designed for language-learning applications and other educational and training software. Works for both adult and child voices, it excels at recognizing native and non-native speakers.

Learn more +

SRI Language Modeling (SRILM)

Toolkit helps build and apply statistical language models for speech recognition, statistical tagging and segmentation, and machine translation. Can be downloaded and used free of charge.

Learn more +

Publications

more +

  • Toward Fail-Safe Speaker Recognition: Trial-Based Calibration with a Reject Option

    November 18, 2022

    In this work, we extend the TBC method, proposing a new similarity metric for selecting training data that results in significant gains over the one proposed in the original work, a new option that…

  • Resilient Data Augmentation Approaches to Multimodal Verification in the News Domain

    October 1, 2021

    Building on multimodal embedding techniques, we show that data augmentation via two distinct approaches improves results: entity linking and cross-domain local similarity scaling.

  • Natural Language Access: When Reasoning Makes Sense

    July 27, 2021

    We argue that to use natural language effectively, we must have both a deep understanding of the subject domain and a general-purpose reasoning capability.

  • Wideband Spectral Monitoring Using Deep Learning

    July 22, 2020

    We present a system to perform spectral monitoring of a wide band of 666.5 MHz, located within a range of 6 GHz of Radio Frequency (RF) bandwidth, using state-of-the-art deep learning approaches.

  • Dual orexin and MCH neuron-ablated mice display severe sleep attacks and cataplexy

    April 21, 2020

    Orexin/hypocretin-producing and melanin-concentrating hormone-producing (MCH) neurons are co-extensive in the hypothalamus and project throughout the brain to regulate sleep/wakefulness.

  • Mapping Individual to Group Level Collaboration Indicators Using Speech Data

    June 1, 2019

    Automatic detection of collaboration quality from the students’ speech could support teachers in monitoring group dynamics, diagnosing issues, and developing pedagogical intervention plans.

  • Robust Speaker Recognition from Distant Speech under Real Reverberant Environments Using Speaker Embeddings

    September 1, 2018

    This article focuses on speaker recognition using speech acquired using a single distant or far-field microphone in an indoors environment. This study differs from the majority of speaker recognition research, which focuses on speech acquisition over short distances, such as when using a telephone handset or mobile device or far-field microphone arrays, for which beamforming can enhance distant speech signals. We use two large-scale corpora collected by retransmitting speech data in reverberant environments with multiple microphones placed at different distances. We first characterize three different speaker recognition systems ranging from a traditional universal background model (UBM) i-vector system to a state-of-the-art deep neural network (DNN) speaker embedding system with a probabilistic linear discriminant analysis (PLDA) back-end. We then assess the impact of microphone distance and placement, background noise, and loudspeaker orientation on the performance of speaker recognition system for distant speech data. We observe that the recently introduced DNN speaker embedding based systems are far more robust compared to i-vector based systems, providing a significant relative improvement of up to 54% over the baseline UBM i-vector system, and 45.5% over prior DNN-based speaker recognition technology.

  • Analysis of Complementary Information Sources in the Speaker Embeddings Framework

    September 1, 2018

    Deep neural network (DNN)-based speaker embeddings have resulted in new, state-of-the-art text-independent speaker recognition technology. However, very limited effort has been made to understand DNN speaker embeddings. In this study, our aim is analyzing the behavior of the speaker recognition systems based on speaker embeddings toward different front-end features, including the standard Mel frequency cepstral coefficients (MFCC), as well as power normalized cepstral coefficients (PNCC), and perceptual linear prediction (PLP). Using a speaker recognition system based on DNN speaker embeddings and probabilistic linear discriminant analysis (PLDA), we compared different approaches to leveraging complementary information using score-, embeddings-, and feature-level combination. We report our results for Speakers in the Wild (SITW) and NIST SRE 2016 datasets. We found that first and second embeddings layers are complementary in nature. By applying score and embedding-level fusion we demonstrate relative improvements in equal error rate of 17% on NIST SRE 2016 and 10% on SITW over the baseline system.

  • Structure-based lead optimization to improve antiviral potency and ADMET properties of phenyl-1H-pyrrole-carboxamide entry inhibitors targeted to HIV-1 gp120

    June 25, 2018

    We are continuing our concerted effort to optimize our first lead entry antagonist, NBD-11021, which targets the Phe43 cavity of the HIV-1 envelope glycoprotein gp120, to improve antiviral potency and ADMET properties. In this report, we present a structure-based approach that helped us to generate working hypotheses to modify further a recently reported advanced lead entry antagonist, NBD-14107, which showed significant improvement in antiviral potency when tested in a single-cycle assay against a large panel of Env-pseudotyped viruses. We report here the synthesis of twenty-nine new compounds and evaluation of their antiviral activity in a single-cycle and multi-cycle assay to derive a comprehensive structure-activity relationship (SAR). We have selected three inhibitors with the high selectivity index for testing against a large panel of 55 Env-pseudotyped viruses representing a diverse set of clinical isolates of different subtypes. The antiviral activity of one of these potent inhibitors, 55 (NBD-14189), against some clinical isolates was as low as 63 nM. We determined the sensitivity of CD4-binding site mutated-pseudoviruses to these inhibitors to confirm that they target HIV-1 gp120. Furthermore, we assessed their ADMET properties and compared them to the clinical candidate attachment inhibitor, BMS-626529. The ADMET data indicate that some of these new inhibitors have comparable ADMET properties to BMS-626529 and can be optimized further to potential clinical candidates.

How can we help?

Once you hit send…

We’ll match your inquiry to the person who can best help you.

Expect a response within 48 hours.

Career call to action image

Make your own mark.

Search jobs

Our work

Case studies

Publications

Timeline of innovation

Areas of expertise

Institute

Leadership

Press room

Media inquiries

Compliance

Careers

Job listings

Contact

SRI Ventures

Our locations

Headquarters

333 Ravenswood Ave
Menlo Park, CA 94025 USA

+1 (650) 859-2000

Subscribe to our newsletter


日本支社
SRI International
  • Contact us
  • Privacy Policy
  • Cookies
  • DMCA
  • Copyright © 2022 SRI International