Picture for Jan Černocký

Jan Černocký

BUT System for the MLC-SLM Challenge

Add code
Jun 16, 2025
Viaarxiv icon

Factors affecting the in-context learning abilities of LLMs for dialogue state tracking

Add code
Jun 10, 2025
Viaarxiv icon

Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs

Add code
Jun 10, 2025
Viaarxiv icon

TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models

Add code
May 10, 2025
Viaarxiv icon

DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition

Add code
Dec 30, 2024
Viaarxiv icon

Aligning Pre-trained Models for Spoken Language Translation

Add code
Nov 27, 2024
Viaarxiv icon

Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models

Add code
Oct 22, 2024
Figure 1 for Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models
Figure 2 for Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models
Figure 3 for Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models
Figure 4 for Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models
Viaarxiv icon

State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data

Add code
Oct 03, 2024
Figure 1 for State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data
Figure 2 for State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data
Figure 3 for State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data
Figure 4 for State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data
Viaarxiv icon

Target Speaker ASR with Whisper

Add code
Sep 14, 2024
Viaarxiv icon

Improving Speaker Verification with Self-Pretrained Transformer Models

Add code
May 17, 2023
Figure 1 for Improving Speaker Verification with Self-Pretrained Transformer Models
Figure 2 for Improving Speaker Verification with Self-Pretrained Transformer Models
Figure 3 for Improving Speaker Verification with Self-Pretrained Transformer Models
Figure 4 for Improving Speaker Verification with Self-Pretrained Transformer Models
Viaarxiv icon