Picture for Emre Yılmaz

Emre Yılmaz

Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages

Mar 06, 2020
Figure 1 for Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages
Figure 2 for Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages
Figure 3 for Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages
Figure 4 for Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages
Viaarxiv icon

End-to-End Code-Switching ASR for Low-Resourced Language Pairs

Add code
Sep 30, 2019
Figure 1 for End-to-End Code-Switching ASR for Low-Resourced Language Pairs
Figure 2 for End-to-End Code-Switching ASR for Low-Resourced Language Pairs
Figure 3 for End-to-End Code-Switching ASR for Low-Resourced Language Pairs
Figure 4 for End-to-End Code-Switching ASR for Low-Resourced Language Pairs
Viaarxiv icon

Large-Scale Speaker Diarization of Radio Broadcast Archives

Jun 28, 2019
Figure 1 for Large-Scale Speaker Diarization of Radio Broadcast Archives
Figure 2 for Large-Scale Speaker Diarization of Radio Broadcast Archives
Figure 3 for Large-Scale Speaker Diarization of Radio Broadcast Archives
Viaarxiv icon

Multi-Graph Decoding for Code-Switching ASR

Add code
Jun 28, 2019
Figure 1 for Multi-Graph Decoding for Code-Switching ASR
Figure 2 for Multi-Graph Decoding for Code-Switching ASR
Figure 3 for Multi-Graph Decoding for Code-Switching ASR
Viaarxiv icon

Acoustic Modeling for Automatic Lyrics-to-Audio Alignment

Jun 25, 2019
Figure 1 for Acoustic Modeling for Automatic Lyrics-to-Audio Alignment
Figure 2 for Acoustic Modeling for Automatic Lyrics-to-Audio Alignment
Figure 3 for Acoustic Modeling for Automatic Lyrics-to-Audio Alignment
Figure 4 for Acoustic Modeling for Automatic Lyrics-to-Audio Alignment
Viaarxiv icon

Semi-supervised acoustic model training for five-lingual code-switched ASR

Jun 20, 2019
Figure 1 for Semi-supervised acoustic model training for five-lingual code-switched ASR
Figure 2 for Semi-supervised acoustic model training for five-lingual code-switched ASR
Figure 3 for Semi-supervised acoustic model training for five-lingual code-switched ASR
Figure 4 for Semi-supervised acoustic model training for five-lingual code-switched ASR
Viaarxiv icon

Code-Switching Detection Using ASR-Generated Language Posteriors

Jun 19, 2019
Figure 1 for Code-Switching Detection Using ASR-Generated Language Posteriors
Figure 2 for Code-Switching Detection Using ASR-Generated Language Posteriors
Figure 3 for Code-Switching Detection Using ASR-Generated Language Posteriors
Figure 4 for Code-Switching Detection Using ASR-Generated Language Posteriors
Viaarxiv icon

Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech

May 21, 2019
Figure 1 for Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech
Figure 2 for Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech
Figure 3 for Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech
Figure 4 for Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech
Viaarxiv icon

Semi-supervised acoustic model training for speech with code-switching

Add code
Oct 23, 2018
Figure 1 for Semi-supervised acoustic model training for speech with code-switching
Figure 2 for Semi-supervised acoustic model training for speech with code-switching
Figure 3 for Semi-supervised acoustic model training for speech with code-switching
Figure 4 for Semi-supervised acoustic model training for speech with code-switching
Viaarxiv icon

Generative x-vectors for text-independent speaker verification

Sep 17, 2018
Figure 1 for Generative x-vectors for text-independent speaker verification
Figure 2 for Generative x-vectors for text-independent speaker verification
Figure 3 for Generative x-vectors for text-independent speaker verification
Figure 4 for Generative x-vectors for text-independent speaker verification
Viaarxiv icon