Skip to main content
Nikolay Shmyrev's user avatar
Nikolay Shmyrev's user avatar
Nikolay Shmyrev's user avatar
Nikolay Shmyrev
  • Member for 9 years, 3 months
  • Last seen more than 3 years ago
4 votes
Accepted

Different fonts of audio from a single audio source

2 votes
Accepted

Understanding hidden markov model, and how it is applied in speech recognition

2 votes
Accepted

Forced alignment HMM

2 votes
Accepted

When use CTC-loss for speech recognition?

2 votes

Does speech recognition model training require transcript timestamps

1 vote
Accepted

Interpolating speech from different speakers in trigger word detection

1 vote
Accepted

How do you evaluate/test accuracy of Text-to-Speech (TTS) models?

1 vote

Speech recognition - hangover scheme - voice activity detection

1 vote

Are e2e DL systems better than DNN-HMM models in speech recognition?

1 vote

How to use GMMs for acoustic signal classification?

1 vote
Accepted

Deciding length of units in sound recognition for training HMMs

1 vote
Accepted

Is there a keyword recognition system without learning the Phoneme

1 vote
Accepted

How to derive the GMM log-likelihood formulation in the eigenvoice modeling technique?

1 vote
Accepted

How to prevent the creation of redundant mixtures while training a GMM?

1 vote

How to normalize text when computing the word error rate of a speech recognition system?

1 vote

Adapt speech recognition for Shakespeare english

1 vote

How are text-to-speech systems' spectrogram frames aligned for loss calculation?

1 vote
Accepted

Mismatching dimensions of input/output in the WaveNet model for text-to-speech generation?

0 votes
Accepted

Transfer learning for audio

0 votes

Verifying Time Warp

0 votes

Why is phase reconstruction considered hard

0 votes
Accepted

Streaming audio to neural network

0 votes

Aggregating LSTM subsequence output into full sequence