Complexity of the TDNN Acoustic Model with Respect to the HMM Topology

von Psutka, Josef V.
Veröffentlicht in TSD (23. : 2020 : Online) Text, speech, and dialogue (2020)

Various DNN-HMM Architectures Used in Acoustic Modeling with Single-Speaker and Single-Channel

von Psutka, Josef V.
Veröffentlicht in International Conference on Statistical Language and Speech Processing (9. : 2021 : Cardiff) Statistical Language and Speech Processing (2021)

Recognition of Heavily Accented and Emotional Speech of English and Czech Holocaust Survivors Using Various DNN Architectures

von Psutka, Josef V.
Veröffentlicht in SPECOM (23. : 2021 : Online) Speech and computer (2021)

CNN-TDNN-Based Architecture for Speech Recognition Using Grapheme Models in Bilingual Czech-Slovak Task

von Psutka, Josef V.
Veröffentlicht in TSD (24. : 2021 : Olomouc; Online) Text, speech, and dialogue (2021)

SPOKEN TERM DETECTION AND RELEVANCE SCORE ESTIMATION USING DOT- PRODUCT OF PRONUNCIA TION EMBEDDINGS

von Svec, Jan
Veröffentlicht in INTERSPEECH (22. : 2021 : Brünn; Online) 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021) ; Volume 2 of 6 (2021)

LIVE TV SUBTITLING THROUGH RESPEAKING

von Prazak, Ales
Veröffentlicht in INTERSPEECH (22. : 2021 : Brünn; Online) 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021) ; Volume 3 of 6 (2021)