Unspeech: Unsupervised Speech Context Embeddings

04/18/2018
by   Benjamin Milde, et al.
0

We introduce "Unspeech" embeddings, which are based on unsupervised learning of context feature representations of spoken language. The embeddings were trained on up to 9500 hours of crawled English speech data without transcriptions or speaker information, by using a straightforward learning objective based on context and non-context discrimination with negative sampling. We use a Siamese convolutional neural network architecture to train Unspeech embeddings and evaluate them on speaker comparison, utterance clustering and as a context feature in TDNN-HMM acoustic models trained on TED-LIUM, comparing it to i-vector baselines. Particularly decoding out-of-domain speech data from the recently released Common Voice corpus shows consistent WER reductions. We release our source code and pre-trained Unspeech models under a permissive open source license.

READ FULL TEXT
research
05/16/2022

PRISM: Pre-trained Indeterminate Speaker Representation Model for Speaker Diarization and Speaker Verification

Speaker embedding has been a fundamental feature for speaker-related tas...
research
11/03/2019

Robust speaker recognition using unsupervised adversarial invariance

In this paper, we address the problem of speaker recognition in challeng...
research
04/07/2022

Detecting Vocal Fatigue with Neural Embeddings

Vocal fatigue refers to the feeling of tiredness and weakness of voice d...
research
07/31/2020

Designing Neural Speaker Embeddings with Meta Learning

Neural speaker embeddings trained using classification objectives have d...
research
02/22/2018

Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics

Learning speaker-specific features is vital in many applications like sp...
research
07/27/2020

Evaluating the reliability of acoustic speech embeddings

Speech embeddings are fixed-size acoustic representations of variable-le...

Please sign up or login with your details

Forgot password? Click here to reset