Runātāju segmentēšana skaņas ierakstā ir audio analīzes problēma, kas paredz ierakstā dzirdamu cilvēka runas fragmentu identificēšanu un grupēšanu gadījumos, kad vairākus fragmentus izteicis viens un tas pats runātājs. Runātāju segmentēšana ir aktuāla problēma audio ierakstu transkripcijas procesā, kur nepieciešams atbildēt uz jautājumu “kas runāja kad?”. Darbā izpētīts mākslīgo neironu tīklu un dziļās mašīnmācīšanās metožu potenciāls un iespējas runātāju segmentēšanas problēmas risināšanā. Tiek apskatīti gatavi runātāju segmentēšanas risinājumi un to darbības pamatprincipi. Praktiskajā daļā tika izveidots uz neironu tīkliem bāzētas runātāju segmentēšanas sistēmas prototips un datu kopa sistēmas apmācībai. Tika salīdzināti apskatīto runātāj...
The objective of speaker diarization is to determine who spoke and when in a given audio stream. Thi...
Speaker diarization is the task of determining "who speaks when" in an audio stream that usually con...
Kvalifikācijas darbā tiek aprakstīta sistēma, tās prasības un realizācija. Šī sistēma sastāv no tīme...
The goal in Speaker Diarization (SD) is to answer the question "Who spoke when?" for a given audio w...
Bu çalışmada konuşma işaretinin incelenmesi ve son günlerde en popüler tanıma yöntemi olan Yapay Sin...
Bu çalışmada TIMIT veri tabanından alınan bir test öbeği üzerinde Yapay Sinir Ağları ve geri yayılım...
Speaker diarization finds contiguous speaker segments in an audio recording and clusters them by spe...
Speaker diarisation answers the question “who spoke when?” in an audio recording. The input may vary...
This paper presents an approach to the speaker diarization problem based on speech local waveform an...
In this paper we present results on speaker identification task by using neural networks for acousti...
Bu çalışmada amacımız bir ses girdi cihazı ile alman konuşmayı metine çevirmektir. Bu amaç doğrultus...
Speaker diarization is the task of determining 'who spoke when' in an audio segment. Since the break...
Speaker diarization is the process of annotating an input audio with information that attributes tem...
Runas sastatīšana ar tekstu jeb runas segmentācija ir problēma, kā atrast vietu, kur audio iera...
Ar runas atpazīšanas palīdzību ir iespējams panākt efektīvāku datu apmaiņu starp datoru un tā lietot...
The objective of speaker diarization is to determine who spoke and when in a given audio stream. Thi...
Speaker diarization is the task of determining "who speaks when" in an audio stream that usually con...
Kvalifikācijas darbā tiek aprakstīta sistēma, tās prasības un realizācija. Šī sistēma sastāv no tīme...
The goal in Speaker Diarization (SD) is to answer the question "Who spoke when?" for a given audio w...
Bu çalışmada konuşma işaretinin incelenmesi ve son günlerde en popüler tanıma yöntemi olan Yapay Sin...
Bu çalışmada TIMIT veri tabanından alınan bir test öbeği üzerinde Yapay Sinir Ağları ve geri yayılım...
Speaker diarization finds contiguous speaker segments in an audio recording and clusters them by spe...
Speaker diarisation answers the question “who spoke when?” in an audio recording. The input may vary...
This paper presents an approach to the speaker diarization problem based on speech local waveform an...
In this paper we present results on speaker identification task by using neural networks for acousti...
Bu çalışmada amacımız bir ses girdi cihazı ile alman konuşmayı metine çevirmektir. Bu amaç doğrultus...
Speaker diarization is the task of determining 'who spoke when' in an audio segment. Since the break...
Speaker diarization is the process of annotating an input audio with information that attributes tem...
Runas sastatīšana ar tekstu jeb runas segmentācija ir problēma, kā atrast vietu, kur audio iera...
Ar runas atpazīšanas palīdzību ir iespējams panākt efektīvāku datu apmaiņu starp datoru un tā lietot...
The objective of speaker diarization is to determine who spoke and when in a given audio stream. Thi...
Speaker diarization is the task of determining "who speaks when" in an audio stream that usually con...
Kvalifikācijas darbā tiek aprakstīta sistēma, tās prasības un realizācija. Šī sistēma sastāv no tīme...