RNN-Transducer (RNN-T) models have become synonymous with streaming end-to-end ASR systems. While they perform competitively on a number of evaluation categories, rare words pose a serious challenge to RNN-T models. One main reason for the degradation in performance on rare words is that the language model (LM) internal to RNN-Ts can be-come overconfident and lead to hallucinated predictions that are acoustically inconsistent with the underlying speech. To address this issue, we propose a lightweight adaptive LM dis-counting technique ADAPTLMD, that can be used with any RNN-T architecture without requiring any external resources or additional parameters. ADAPTLMD uses a two-pronged approach: 1. Randomly mask the prediction network output to encourage the RNN-T to not be overly reliant on it’s outputs. 2. Dynamically choose when to discount the implicit LM (ILM) based on rarity of recently predicted tokens and divergence between ILM and implicit acoustic model (IAM) scores. Comparing ADAPTLMD to a competitive RNN-T baseline, we obtain up to 4% and 14% relative reductions in overall WER and rare word PER, respectively, on a conversational, code-mixed Hindi-English ASR task.

Nikhil Saini, Drumil Trivedi, Shreya Khare, Tejas Dhamecha, Preethi Jyothi, Samarth Bharadwaj, Pushpak Bhattacharyya. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking advantage of low amounts of labeled corpora in multiple languages. With multilingualism becoming common in today's world, there has been increasing interest in code-switching ASR as well. In code-switching, multiple languages are freely interchanged within a single sentence or between sentences. The success of low-resource multilingual and code-switching ASR often depends on the variety of languages in terms of their acoustics, linguistic characteristics as well as the amount of data available and how these are carefully considered in building the ASR system. In this challenge, we would like to focus on building multilingual and code-switching ASR systems through two different subtasks related to a total of seven Indian languages, namely Hindi, Marathi, Odia, Tamil, Telugu, Gujarati and Bengali. For this purpose, we provide a total of ~600 hours of transcribed speech data, comprising train and test sets, in these languages including two code-switched language pairs, Hindi-English and Bengali-English. We also provide a baseline recipe for both the tasks with a WER of 30.73% and 32.45% on the test sets of multilingual and code-switching subtasks, respectively.

Spoken intent detection has become a popular approach to interface with various smart devices with ease. However, such systems are limited to the preset list of intents-terms or commands, which restricts the quick customization of personal devices to new intents. This paper presents a few-shot spoken intent classification approach with task-agnostic representations via meta-learning paradigm. Specifically, we leverage the popular representation-based meta-learning learning to build a task-agnostic representation of utterances, that then use a linear classifier for prediction. We evaluate three such approaches on our novel experimental protocol developed on two popular spoken intent classification datasets: Google Commands and the Fluent Speech Commands dataset. For a 5-shot (1-shot) classification of novel classes, the proposed framework provides an average classification accuracy of 88.6% (76.3%) on the Google Commands dataset, and 78.5% (64.2%) on the Fluent Speech Commands dataset. The performance is comparable to traditionally supervised classification models with abundant training samples.

Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains. Both black-box and white-box approaches have been used to either replicate the model itself or to craft examples which cause the model to fail. In this work, we propose a framework which uses multi-objective evolutionary optimization to perform both targeted and un-targeted black-box attacks on Automatic Speech Recognition (ASR) systems. We apply this framework on two ASR systems: Deepspeech and Kaldi-ASR, which increases the Word Error Rates (WER) of these systems by upto 980%, indicating the potency of our approach. During both un-targeted and targeted attacks, the adversarial samples maintain a high acoustic similarity of 0.98 and 0.97 with the original audio.

Question answering is one of the primary challenges of natural language understanding. In realizing such a system, providing complex long answers to questions is a challenging task as opposed to factoid answering as the former needs context disambiguation. The different methods explored in the literature can be broadly classified into three categories namely: 1) classification based, 2) knowledge graph based and 3) retrieval based. Individually, none of them address the need of an enterprise wide assistance system for an IT support and maintenance domain. In this domain, the variance of answers is large ranging from factoid to structured operating procedures; the knowledge is present across heterogeneous data sources like application specific documentation, ticket management systems and any single technique for a general purpose assistance is unable to scale for such a landscape. To address this, we have built a cognitive platform with capabilities adopted for this domain. Further, we have built a general purpose question answering system leveraging the platform that can be instantiated for multiple products, technologies in the support domain. The system uses a novel hybrid answering model that orchestrates across a deep learning classifier, a knowledge graph based context disambiguation module and a sophisticated bag-of-words search system. This orchestration performs context switching for a provided question and also does a smooth hand-off of the question to a human expert if none of the automated techniques can provide a confident answer. This system has been deployed across 675 internal enterprise IT support and maintenance projects.

With an abundance of research papers in deep learning, adoption and reproducibility of existing works becomes a challenge. To make a DL developer life easy, we propose a novel system, DARVIZ, to visually design a DL model using a drag-and-drop framework in an platform agnostic manner. The code could be automatically generated in both Caffe and Keras. DARVIZ could import (i) any existing Caffe code, or (ii) a research paper containing a DL design; extract the design, and present it in visual editor.

With an abundance of research papers in deep learning, reproducibility or adoption of the existing works becomes a challenge. This is due to the lack of open source implementations provided by the authors. Even if the source code is available, then re-implementing research papers in a different library is a daunting task. To address these challenges, we propose a novel extensible approach, DLPaper2Code, to extract and understand deep learning design flow diagrams and tables available in a research paper and convert them to an abstract computational graph. The extracted computational graph is then converted into execution ready source code in both Keras and Caffe, in real-time. An arXiv-like website is created where the automatically generated designs is made publicly available for 5,000 research papers. The generated designs could be rated and edited using an intuitive drag-and-drop UI framework in a crowd sourced manner. To evaluate our approach, we create a simulated dataset with over 216,000 valid deep learning design flow diagrams using a manually defined grammar. Experiments on the simulated dataset show that the proposed framework provide more than 93% accuracy in flow diagram content extraction.

This paper identifies moving objects in a video that are associated to the corresponding audio, by exploiting the correlation of audio and video features. The proposed technique is based on the correlation of motion features of eigen moving objects with audio mel frequency cepstral coefficients features using canonical correlation analysis. We propose two strategies to detect the eigen moving objects: (i) Per-frame mapped eigen moving object (PFEMO) and (ii) Temporally coherent eigen moving object (TCEMO). While PFEMO segments each frame using superpixel segmentation, TCEMO exploits supervoxel based video segmentation to identify eigen moving objects. Qualitative (mean-opinion score) and quantitative (precision, recall, area under the curve, hit ratio) analysis shows that the performance of the proposed techniques is superior to those of the state-of-the-art methods.