Interpretability and Robustness in Audio, Speech, and Language

Domains of natural and spoken language processing have a rich history deeply rooted in information theory, statistics, digital signal processing and machine learning. With the rapid rise of deep learning (“deep learning revolution”), many of these systematic approaches have been replaced by variants of deep neural methods, that often achieve unprecedented performance levels in many fields. With more and more of the spoken language processing pipeline being replaced by sophisticated neural layers, feature extraction, adaptation, noise robustness are learnt inherently within the network. More recently, end-to-end frameworks that learn a mapping from speech (audio) to target labels (words, phones, graphemes, sub-word units, etc.) are becoming increasingly popular across the board in speech processing in tasks ranging from speech recognition, speaker identification, language/dialect identification, multilingual speech processing, code switching, natural language processing, speech synthesis and much much more.

A key aspect behind the success of deep learning lies in the discovered low and high-level representations, that can potentially capture relevant underlying structure in the training data. In the NLP domain, for instance, researchers have mapped word and sentence embeddings to semantic and syntactic similarity and argued that the models capture latent representations of meaning. Nevertheless, some recent works on adversarial examples have shown that it is possible to easily fool a neural network (such as a speech recognizer or a speaker verification system) by just adding a small amount of specially constructed noise. Such a remarkable sensibility towards adversarial attacks highlights how superficial the discovered representations could be, rising crucial concerns on the actual robustness, security, and interpretability of modern deep neural networks. This weakness naturally leads researchers to ask very crucial questions on what these models are really learning, how we can interpret what they have learned, and how the representations provided by current neural networks can be revealed or explained in a fashion that modeling power can be enhanced further. These open questions have recently raised the interest towards interpretability of deep models, as witness by the numerous works recently published on this topic in all the major machine learning conferences. Moreover, some workshops at NIPS 2016, NIPS 2017 and Interspeech 2017 have promoted research and discussion around this important issue.
With our initiative, we wish to further foster some progresses on interpretability and robustness of modern deep learning techniques, with a particular focus on audio, speech and NLP technologies. The workshop will also analyze the connection between deep learning and models developed earlier for machine learning, linguistic analysis, signal processing, and speech recognition. This way we hope to encourage a discussion amongst experts and practitioners in these
areas with the expectation of understanding these models better and allowing to build upon the existing collective expertise.

The workshop will feature invited talks, panel discussions, as well as oral and poster contributed presentations. We welcome papers that specifically address one or more of the leading questions listed below:
1. Is there a theoretical/linguistic motivation/analysis that can explain how nets encapsulate the structure of the training data it learns from?
2. Does the visualization of this information (MDS, t-SNE) offer any insights to creating a better model?
3. How can we design more powerful networks with simpler architectures?
4. How can we can exploit adversarial examples to improve the system robustness?
5. Do alternative methods offer any complimentary modeling power to what the networks can memorize?
6. Can we explain the path of inference?
7. How do we analyze data requirements for a given model? How does multilingual data improves learning power?