37 citations · 58 across the 7 of their papers we have counts for
10 papers
End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Tamás Grósz, Mittul Singh, Sudarsana Reddy Kadiri +2
The events of recent years have highlighted the importance of telemedicine solutions which could potentially allow remote treatment and diagnosis. Relatedly, Computational Paraling…
Data augmentation using prosody and false starts to recognize non-native children's speech
Hemant Kathania, Mittul Singh, Tamás Grósz +1
This paper describes AaltoASR's speech recognition system for the INTERSPEECH 2020 shared task on Automatic Speech Recognition (ASR) for non-native children's speech. The task is t…
FinChat: Corpus and evaluation setup for Finnish chat conversations on everyday topics
Katri Leino, Juho Leinonen, Mittul Singh +2
Creating open-domain chatbots requires large amounts of conversational data and related benchmark tasks to evaluate them. Standardized evaluation tasks are crucial for creating aut…
Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge
Tamás Grósz, Mittul Singh, Sudarsana Reddy Kadiri +2
End-to-end neural network models (E2E) have shown significant performance benefits on different INTERSPEECH ComParE tasks. Prior work has applied either a single instance of an E2E…
Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models
Mittul Singh, Peter Smit, Sami Virpioja +1
Character-based Neural Network Language Models (NNLM) have the advantage of smaller vocabulary and thus faster training times in comparison to NNLMs based on multi-character units.…
Subword RNNLM Approximations for Out-Of-Vocabulary Keyword Search
Mittul Singh, Sami Virpioja, Peter Smit +1
In spoken Keyword Search, the query may contain out-of-vocabulary (OOV) words not observed when training the speech recognition system. Using subword language models (LMs) in the f…
Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling
Debjit Paul, Mittul Singh, Michael A. Hedderich +1
In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount…
Long-Short Range Context Neural Networks for Language Modeling
Youssef Oualil, Mittul Singh, Clayton Greenberg +1
The goal of language modeling techniques is to capture the statistical and structural properties of natural languages from training corpora. This task typically involves the learni…
Sequential Recurrent Neural Networks for Language Modeling
Youssef Oualil, Clayton Greenberg, Mittul Singh +1
Feedforward Neural Network (FNN)-based language models estimate the probability of the next word based on the history of the last N words, whereas Recurrent Neural Networks (RNN) p…
Effective Slot Filling Based on Shallow Distant Supervision Methods
Benjamin Roth, Tassilo Barth, Michael Wiegand +2
Spoken Language Systems at Saarland University (LSV) participated this year with 5 runs at the TAC KBP English slot filling track. Effective algorithms for all parts of the pipelin…