Speaker recognition with recurrent neural networks
By Shahla Parveen, Abdul Qadeer, Phil D. Green. 2000
18 citations recorded by the source corpus.
We report on the application of recurrent neural nets in a open-set text-dependent speaker identification task. The motivation for applying recurrent neural nets to this domain is to find out if their ability to take short-term spectral features but yet respond to long-term temporal events is advantageous for speaker identification. We use a feedforward net architecture adapted from that intro-duced by Robinson et.al. We introduce a fully-connected hidden layer between the input and state nodes and the output. We show that this hidden layer makes the learning of complex classification tasks more efficient. Training uses back propagation through time. There is one output unit per speaker, with the training targets corresponding to speaker identity. For 12 speakers (a mixture of male and female) we obtain a true acceptance rate 100% with a false acceptance rate 4%. For 16 speakers these figures are 94% and 7% respectively. We also investigate the sensitivity of identification accuracy to environmental factors (signal level, change of microphone and band limitation), choice of acoustic vectors (FFT, LPC or Ceps-tral), distribution of speakers in the training database, inclusion of fundamental frequency. FFT features plus fundamental frequency give the best results. This performance is shown to compare favorably with studies reported on similar tasks with Hidden Markov Model technique.
Subfields: Artificial Intelligence, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Quoc V. Le
- Noam Shazeer
- Mohit Bansal
- Yoshua Bengio
- Jianfeng Gao
- Samy Bengio
- James R. Glass
- Luke S. Zettlemoyer
In Signal Processing
- Samy Bengio
- Noam Shazeer
- Georg Heigold
- Ignacio Moreno
- Karen Livescu
- James R. Glass
- Yoshua Bengio
- Yu-An Chung
Citations in the corpus
- End-to-end text-dependent speaker verification (2015, background): “To the best of our knowledge, recurrent neural networks have been applied to related problems such as speaker identification [16] and language identification [17], but not to the speaker verification task.”