Contextual Joint Factor Acoustic Embeddings
Yanpei Shi,Thomas Hain +1 more
- pp 750-757
Reads0
Chats0
TLDR
In this paper, two unsupervised approaches to generate acoustic embeddings by modeling of acoustic context are proposed, one is a contextual joint factor synthesis encoder, where the encoder in an encoder/decoder framework is trained to extract joint factors from surrounding audio frames to best generate the target output.Abstract:
Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic context are proposed. The first approach is a contextual joint factor synthesis encoder, where the encoder in an encoder/decoder framework is trained to extract joint factors from surrounding audio frames to best generate the target output. The second approach is a contextual joint factor analysis encoder, where the encoder is trained to analyse joint factors from the source signal that correlates best with the neighbouring audio. To evaluate the effectiveness of our approaches compared to prior work, two tasks are conducted-phone classification and speaker recognition - and test on different TIMIT data sets. Experimental results show that one of the proposed approaches outperforms phone classification baselines, yielding a classification accuracy of 74.1%. When using additional out-of-domain data for training, an additional 3% improvements can be obtained, for both for phone classification and speaker recognition tasks.read more
Citations
More filters
Journal ArticleDOI
Improved Acoustic Word Embeddings for Zero-Resource Languages Using Multilingual Transfer
TL;DR: In this paper, three multilingual recurrent neural network (RNN) models: a classifier trained on the joint vocabularies of all training languages; a Siamese RNN trained to discriminate between same and different words from multiple languages; and a correspondence autoencoder(CAE) trained to reconstruct word pairs.
Posted Content
Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language
Christiaan Jacobs,Herman Kamper +1 more
TL;DR: This paper showed that training on even just a single related language gives the largest gain over training on unrelated languages, and that adding data from unrelated languages generally does not hurt performance in word discrimination and query-by-example search evaluations.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Proceedings ArticleDOI
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.