Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Conv-TasNet Akoko-ašẹ-ašẹ Iyapa adanwo

Review Conv-TasNet’s learned waveform encoder, masked separation features, TCN separator, and the scope of its benchmark results.

Jẹmọ itọsọna awọn ọnaConv Tasnet Aago ase Iyapa
Ibeere 1 ti 8

Kini ẹya asọye ti Conv-TasNet ni akawe si awọn eto iyapa iṣaaju?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Kini ẹya asọye ti Conv-TasNet ni akawe si awọn eto iyapa iṣaaju?
    • O nṣiṣẹ taara lori aise igbi fọọmu dipo ti a ti o wa titi spectrogram
    • Ko nilo data ikẹkọ
    • O ṣiṣẹ nikan lori orin, kii ṣe ọrọ
    • O ṣe iyipada ohun si MIDI ni akọkọ
  2. Iru nẹtiwọki wo ni Conv-TasNet lo bi module iyapa rẹ?
    • A nikan ni kikun ti sopọ Layer
    • Nẹtiwọọki Convolutional Igba diẹ (awọn itọka 1D ti o gbooro)
    • A akojọpọ igi ipinnu
    • A awoṣe itankale
  3. Kini o rọpo Iyipada Aago Kukuru ti aṣa ni Conv-TasNet?
    • A wavelet yipada
    • Ferese Hann kan
    • Ayipada 1D-convolution koodu
    • A Mel filterbank
  4. Iṣẹ pipadanu wo ni aringbungbun si ikẹkọ Conv-TasNet?
    • Cross-entropy lori awọn aami ọrọ
    • Itumosi asise piksẹli pipe
    • Pipadanu aworan itansan
    • Iwọn-ayipada SI-SNR pẹlu permutation-ayipada ikẹkọ
  5. What did Conv-TasNet’s paper report about ideal time-frequency magnitude masks?
    • It surpassed several ideal magnitude masks in two-speaker separation evaluations
    • O pa iwulo fun awọn gbohungbohun kuro
    • It only worked on one identical speaker
    • It used ideal masks as its encoder
  6. What does Conv-TasNet’s learned encoder produce for the separator?
    • A transcript of each speaker
    • A waveform representation optimized for speaker separation
    • A fixed mel image
    • A list of microphone locations
  7. What type of speech-separation task did the Conv-TasNet paper address?
    • Text-to-speech from a written prompt
    • Speaker identification from video frames
    • A single-channel mixture containing multiple speakers
    • Multichannel music transcription with MIDI output
  8. What allows Conv-TasNet’s TCN to model long-term speech dependencies?
    • A database lookup for every audio sample
    • A text decoder
    • A fixed Fourier transform alone
    • Stacked one-dimensional dilated convolutional blocks