Deep Learning Practice Quiz 2: 16 August 2026 (May 2026 term)

Select all that apply.

1. A

   Background noise

2. B

   Very short utterances

3. C

   Code-switching

4. D

   Large balanced training data

Select all that apply.

1. A

   Voice Activity Detection (VAD) / Segmentation

2. B

   Speech Recognition and Timestamp Generation

3. C

   Speaker Embedding Extraction

4. D

   Language Identification

5. E

   Speaker Clustering

6. F

   Text-to-Speech (TTS) Synthesis

7. G

   Alignment and Segment Merging

Select all that apply.

1. A

   The system is trained on single-channel (mono) recordings.

2. B

   The user must manually extract acoustic features (like MFCCs or Mel- filterbanks) before passing the data to the model.

3. C

   The expected sampling rate for the input audio is 16kHz.

4. D

   The model accepts variable-length audio inputs, dynamically generating fixed- size embeddings regardless of the utterance duration.