Guide-yakabatana mibvunzo · Zvakaoma Nhanho

Permutation Invariant Training Quiz

Edza kuti dzidziso yekubvumidza-inochinja-chinja inoita sei zvinobuda zvisina kurongeka zvemutauri uye nei basa rekutaura richikosha panguva yekuparadzaniswa kwevatauri vakawanda.

Nzira dzekutungamira dzinoenderanaPermutation Invariant Training
Mubvunzo 1 ye 8

Nderipi dambudziko guru rinogadziriswa nepermutation invariant training (PIT)?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Nderipi dambudziko guru rinogadziriswa nepermutation invariant training (PIT)?
    • Kusarudza kuti ndeipi nzira yekubuda inofanirwa kuenderana nemutauri panguva yekudzidziswa
    • Kudzvanya odhiyo yekuchengetedza
    • Kuderedza mari yemakrofoni hardware
    • Kushandura mutauro wakapatsanurwa kuita mavara
  2. PIT inosarudza sei kukanganisa kwekushandisa paunenge uchivandudza modhi?
    • Inoita avhareji yekukanganisa pane zvese zvinobuda zvakaenzana
    • Inoedza zvese zvinobuda-kune-source pairing uye inochengeta iyo ine yakaderera kukanganisa
    • Iyo inogara ichipa izwi rine ruzha kuburitsa 1
    • Iyo inofuratira mareferensi zvachose
  3. Pasina mhinduro yakaita sePIT, chii chaida kuitika kune kupatsanurwa modhi zvinobuda?
    • Vakabva vanyatsochena pakarepo
    • Vakamhanya zvakanyanya
    • Ivo vakaburitsa blurry, avhareji yezvakabuda nekuda kwekupokana kwemazita ekupa
    • Vaisada ruzivo rwekudzidziswa
  4. Pakuparadzanisa vatauri veN, vangani mvumo inofanirwa kutariswa nePIT padanho rega rega?
    • N (mutsara muvatauri)
    • N squared
    • Nguva dzose maviri chaiwo
    • N factorial
  5. Ndeipi mukana wekutaura-level PIT (UPIT) inowedzera pamusoro peiyo furemu-level basa?
    • Inochengeta mutauri muchiteshi chakatsiga chinobuda pakutaura kwese
    • Inobvisa kudiwa kwechero mareferensi
    • Inoshanda chete pamimhanzi, kwete kutaura
    • Inopeta kaviri nhamba yevatauri
  6. Ndeipi nzira inogona kudzikamisa dambudziko rekubvumidza zvachose?
    • Kuwedzera audio bitrate
    • Mutauriri wemutauriri wemutauriri anoisa pareferensi yezwi
    • Kushandisa monorekodha chete
    • Kudzivisa backpropagation
  7. What extra inference step does utterance-level PIT avoid compared with frame-level PIT?
    • Running speech recognition before source separation
    • Estimating the number of microphones in the recording
    • Solving an additional output-speaker permutation problem during inference
    • Recomputing the training loss after every generated word
  8. Which benchmark does the guide name as an example for evaluating speech-separation models?
    • LibriSpeech for single-speaker transcription
    • ImageNet for visual recognition
    • GLUE for language understanding
    • WSJ0-2mix for overlapping-speaker separation