skip to main content

Title: A DNN-HMM-DNN Hybrid Model for Discovering Word-Like Units from Spoken Captions and Image Regions
Discovering word-like units without textual transcriptions is an important step in low-resource speech technology. In this work,we demonstrate a model inspired by statistical machine translation and hidden Markov model/deep neural network (HMM-DNN) hybrid systems. Our learning algorithm is capable of discovering the visual and acoustic correlates of distinct words in an unknown language by simultaneously learning the map-ping from image regions to concepts (the first DNN), the map-ping from acoustic feature vectors to phones (the second DNN),and the optimum alignment between the two (the HMM). In the simulated low-resource setting using MSCOCO and Speech-COCO datasets, our model achieves 62.4 % alignment accuracy and outperforms the audio-only segmental embedded GMM approach on standard word discovery evaluation metrics.  more » « less
Award ID(s):
Author(s) / Creator(s):
Date Published:
Journal Name:
Page Range / eLocation ID:
1456 to 1460
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The application of deep learning to automatic speech recognition (ASR) has yielded dramatic accuracy increases for languages with abundant training data, but languages with limited training resources have yet to see accuracy improvements on this scale. In this paper, we compare a fully convolutional approach for acoustic modelling in ASR with a variety of established acoustic modeling approaches. We evaluate our method on Seneca, a low-resource endangered language spoken in North America. Our method yields word error rates up to 40% lower than those reported using both standard GMM-HMM approaches and established deep neural methods, with a substantial reduction in training time. These results show particular promise for languages like Seneca that are both endangered and lack extensive documentation. 
    more » « less
  2. Although the application of deep learning to automatic speech recognition (ASR) has resulted in dramatic reductions in word error rate for languages with abundant training data, ASR for languages with few resources has yet to benefit from deep learning to the same extent. In this paper, we investigate various methods of acoustic modeling and data augmentation with the goal of improving the accuracy of a deep learning ASR framework for a low-resource language with a high baseline word error rate. We compare several methods of generating synthetic acoustic training data via voice transformation and signal distortion, and we explore several strategies for integrating this data into the acoustic training pipeline. We evaluate our methods on an indigenous language of North America with minimal training resources. We show that training initially via transfer learning from an existing high-resource language acoustic model, refining weights using a heavily concentrated synthetic dataset, and finally fine-tuning to the target language using limited synthetic data reduces WER by 15% over just transfer learning using deep recurrent methods. Further, we show improvements over traditional frameworks by 19% using a similar multistage training with deep convolutional approaches. 
    more » « less
  3. We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and zero-resource languages. Our model, which we refer to as a maximal sampling correspondence variational autoencoder (MCVAE), is a recurrent neural network (RNN) trained with a novel self-supervised correspondence loss that encourages consistency between embeddings of different instances of the same word. Our training scheme improves on previous correspondence training approaches through the use and comparison of multiple samples from the approximate posterior distribution. In the zero-resource setting, the MCVAE can be trained in an unsupervised way, without any ground-truth word pairs, by using the word-like segments discovered via an unsupervised term discovery system. In both this setting and a semi-supervised low-resource setting (with a limited set of ground-truth word pairs), the MCVAE outperforms previous state-of-the-art models, such as Siamese-, CAE- and VAE-based RNNs. 
    more » « less
  4. Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing and discovery systems. Here we propose to train a single supervised embedding model on labelled data from multiple well-resourced languages and then apply it to unseen zero-resource languages. For this transfer learning approach, we consider two multilingual recurrent neural network models: a discriminative classifier trained on the joint vocabularies of all training languages, and a correspondence autoencoder trained to reconstruct word pairs. We test these using a word discrimination task on six target zero-resource languages. When trained on seven well-resourced languages, both models perform similarly and outperform unsupervised models trained on the zero-resource languages. With just a single training language, the second model works better, but performance depends more on the particular training--testing language pair. 
    more » « less
  5. This paper proposes a novel linear prediction coding-based data augmentation method for children’s low and zero resource dialect ASR. The data augmentation procedure consists of perturbing the formant peaks of the LPC spectrum during LPC analysis and reconstruction. The method is evaluated on two novel children’s speech datasets with one containing California English from the Southern California Area and the other containing a mix of Southern American English and African American English from the Atlanta, Georgia area. We test the proposed method in training both an HMM-DNN system and an end-to-end system to show model-robustness and demonstrate that the algorithm improves ASR performance, especially for zero resource dialect children’s task, as compared to common data augmentation methods such as VTLP, Speed Perturbation, and SpecAugment. 
    more » « less