Picture for Andreas Stolcke

Andreas Stolcke

SRI International, Menlo Park, CA 94025

Improving speaker verification robustness with synthetic emotional utterances

Add code
Nov 30, 2024
Figure 1 for Improving speaker verification robustness with synthetic emotional utterances
Figure 2 for Improving speaker verification robustness with synthetic emotional utterances
Figure 3 for Improving speaker verification robustness with synthetic emotional utterances
Figure 4 for Improving speaker verification robustness with synthetic emotional utterances
Viaarxiv icon

Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings

Add code
Nov 21, 2024
Figure 1 for Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings
Figure 2 for Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings
Figure 3 for Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings
Figure 4 for Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings
Viaarxiv icon

Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward

Add code
Nov 06, 2024
Figure 1 for Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
Figure 2 for Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
Figure 3 for Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
Figure 4 for Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
Viaarxiv icon

Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output

Add code
Nov 01, 2024
Viaarxiv icon

REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models

Add code
Oct 16, 2024
Figure 1 for REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models
Figure 2 for REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models
Figure 3 for REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models
Figure 4 for REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models
Viaarxiv icon

Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition

Add code
Sep 17, 2024
Figure 1 for Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition
Figure 2 for Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition
Figure 3 for Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition
Figure 4 for Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition
Viaarxiv icon

Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion

Add code
Jan 26, 2024
Figure 1 for Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
Figure 2 for Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
Figure 3 for Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
Figure 4 for Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
Viaarxiv icon

Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models

Add code
Jan 23, 2024
Figure 1 for Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models
Figure 2 for Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models
Viaarxiv icon

Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognition

Add code
Jan 19, 2024
Viaarxiv icon

Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue

Add code
Jan 17, 2024
Viaarxiv icon