Picture for Ryan Langman

Ryan Langman

Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference

Add code
Sep 18, 2024
Viaarxiv icon

Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations

Add code
Jul 03, 2024
Figure 1 for Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
Figure 2 for Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
Figure 3 for Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
Figure 4 for Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
Viaarxiv icon

Spectral Codecs: Spectrogram-Based Audio Codecs for High Quality Speech Synthesis

Add code
Jun 07, 2024
Viaarxiv icon

Improving fairness in speaker verification via Group-adapted Fusion Network

Add code
Feb 23, 2022
Figure 1 for Improving fairness in speaker verification via Group-adapted Fusion Network
Figure 2 for Improving fairness in speaker verification via Group-adapted Fusion Network
Figure 3 for Improving fairness in speaker verification via Group-adapted Fusion Network
Figure 4 for Improving fairness in speaker verification via Group-adapted Fusion Network
Viaarxiv icon