Picture for Geonmin Kim

Geonmin Kim

Shortened LLaMA: A Simple Depth Pruning for Large Language Models

Add code
Feb 05, 2024
Viaarxiv icon

Encoder-decoder multimodal speaker change detection

Jun 01, 2023
Figure 1 for Encoder-decoder multimodal speaker change detection
Figure 2 for Encoder-decoder multimodal speaker change detection
Figure 3 for Encoder-decoder multimodal speaker change detection
Figure 4 for Encoder-decoder multimodal speaker change detection
Viaarxiv icon

Back from the future: bidirectional CTC decoding using future information in speech recognition

Oct 07, 2021
Figure 1 for Back from the future: bidirectional CTC decoding using future information in speech recognition
Figure 2 for Back from the future: bidirectional CTC decoding using future information in speech recognition
Figure 3 for Back from the future: bidirectional CTC decoding using future information in speech recognition
Figure 4 for Back from the future: bidirectional CTC decoding using future information in speech recognition
Viaarxiv icon

Spell my name: keyword boosted speech recognition

Oct 06, 2021
Figure 1 for Spell my name: keyword boosted speech recognition
Figure 2 for Spell my name: keyword boosted speech recognition
Figure 3 for Spell my name: keyword boosted speech recognition
Figure 4 for Spell my name: keyword boosted speech recognition
Viaarxiv icon

Semi-supervised Disentanglement with Independent Vector Variational Autoencoders

Add code
Mar 14, 2020
Figure 1 for Semi-supervised Disentanglement with Independent Vector Variational Autoencoders
Figure 2 for Semi-supervised Disentanglement with Independent Vector Variational Autoencoders
Figure 3 for Semi-supervised Disentanglement with Independent Vector Variational Autoencoders
Figure 4 for Semi-supervised Disentanglement with Independent Vector Variational Autoencoders
Viaarxiv icon

Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition

Add code
Nov 06, 2018
Figure 1 for Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
Figure 2 for Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
Figure 3 for Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
Figure 4 for Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
Viaarxiv icon

Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations

Jul 12, 2016
Figure 1 for Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations
Figure 2 for Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations
Figure 3 for Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations
Figure 4 for Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations
Viaarxiv icon

Compositional Sentence Representation from Character within Large Context Text

Jun 03, 2016
Figure 1 for Compositional Sentence Representation from Character within Large Context Text
Figure 2 for Compositional Sentence Representation from Character within Large Context Text
Figure 3 for Compositional Sentence Representation from Character within Large Context Text
Figure 4 for Compositional Sentence Representation from Character within Large Context Text
Viaarxiv icon