WAVLab | 2018 Papers

ML Physica

Model parameter learning using Kullback–Leibler divergence

Chungwei Lin, Tim K Marks, Milutin Pajovic, Shinji Watanabe, and Chih-kuan Tung

Physica A: Statistical Mechanics and its Applications 2018
ASR SLT

End-to-end speech recognition with word-based RNN language models

Takaaki Hori, Jaejin Cho, and Shinji Watanabe

In Proceedings of IEEE Spoken Language Technology Workshop (SLT) 2018
ASR SLT

Low-resource contextual topic identification on speech

Chunxi Liu, Matthew Wiesner, Shinji Watanabe, Craig Harman, Jan Trmal, Najim Dehak, and Sanjeev Khudanpur

In Proceedings of IEEE Spoken Language Technology Workshop (SLT) 2018
ASR SLT

Back-translation-style data augmentation for end-to-end ASR

Tomoki Hayashi, Shinji Watanabe, Yu Zhang, Tomoki Toda, Takaaki Hori, Ramon Astudillo, and Kazuya Takeda

In Proceedings of IEEE Spoken Language Technology Workshop (SLT) 2018
ASR SLT

Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling

Jaejin Cho, Murali Karthick Baskar, Ruizhi Li, Matthew Wiesner, Sri Harish Mallidi, Nelson Yalta, Martin Karafiat, Shinji Watanabe, and Takaaki Hori

In Proceedings of IEEE Spoken Language Technology Workshop (SLT) 2018
ASR Interspeech

ESPnet: End-to-End Speech Processing Toolkit

Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, Jiro Nishitoba, Yuya Unno, Nelson Enrique Yalta Soplin, Jahn Heymann, Matthew Wiesner, Nanxin Chen, Adithya Renduchintala, and Tsubasa Ochiai

Proceedings of Interspeech 2018

Abs arXiv HTML PDF Code

This paper introduces a new open source platform for end-to-end speech processing named ESPnet. ESPnet mainly focuses on end-to-end automatic speech recognition (ASR), and adopts widely-used dynamic neural network toolkits, Chainer and PyTorch, as a main deep learning engine. ESPnet also follows the Kaldi ASR toolkit style for data processing, feature extraction/format, and recipes to provide a complete setup for speech recognition and other speech processing experiments. This paper explains a major architecture of this software platform, several important functionalities, which differentiate ESPnet from other open source ASR toolkits, and experimental results with major ASR benchmarks.
ASR Interspeech

Building State-of-the-art Distant Speech Recognition Using the CHiME-4 Challenge with a Setup of Speech Enhancement Baseline

Szu-Jui Chen, Aswin Shanmugam Subramanian, Hainan Xu, and Shinji Watanabe

Proceedings of Interspeech 2018
ASR Interspeech

Multi-Head Decoder for End-to-End Speech Recognition

Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, and Kazuya Takeda

Proceedings of Interspeech 2018
ASR Interspeech

Semi-Supervised End-to-End Speech Recognition

Shigeki Karita, Shinji Watanabe, Tomoharu Iwata, Atsunori Ogawa, and Marc Delcroix

Proceedings of Interspeech 2018
SE&ASR Interspeech

The Fifth ’CHiME’ Speech Separation and Recognition Challenge: Dataset, Task and Baselines

Jon Barker, Shinji Watanabe, Emmanuel Vincent, and Jan Trmal

Proceedings of Interspeech 2018

arXiv HTML PDF
SE Interspeech

Student-Teacher Learning for BLSTM Mask-based Speech Enhancement

Aswin Shanmugam Subramanian, Szu-Jui Chen, and Shinji Watanabe

Proceedings of Interspeech 2018
ASR Interspeech

Multi-Modal Data Augmentation for End-to-end ASR

Adithya Renduchintala, Shuoyang Ding, Matthew Wiesner, and Shinji Watanabe

Proceedings of Interspeech 2018
LID Interspeech

Effectiveness of single-channel blstm enhancement for language identification

Peter Sibbern Frederiksen, Jesús Villalba, Shinji Watanabe, Zheng-Hua Tan, and Najim Dehak

In Interspeech 2018 2018
SD Interspeech

Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge.

Gregory Sell, David Snyder, Alan McCree, Daniel Garcia-Romero, Jesús Villalba, Matthew Maciejewski, Vimal Manohar, Najim Dehak, Daniel Povey, Shinji Watanabe, and others

In Interspeech 2018

Abs HTML PDF

We describe in this paper the experiences of the Johns Hopkins University team during the inaugural DIHARD diarization evaluation. This new task provided microphone recordings in a variety of difficult conditions and challenged researchers to fully consider all speaker activity, without the currently typical practices of unscored collars or ignored overlapping speaker segments. This paper explores several key aspects of currently state-of-the-art diarization methods, such as training data selection, signal bandwidth for feature extraction, representations of speech segments (i-vector versus x-vector) and domain-adaptive processing. In the end, our best system clustered x-vector embeddings trained on wideband microphone data followed by Variational-Bayesian refinement and a speech activity detector specifically trained for this task with in-domain data was found to be the best performing. After presenting these decisions and their final result, we discuss lessons learned and remaining challenges within the lens of this new approach to diarization performance measurement.
ASR Interspeech

Auxiliary Feature Based Adaptation of End-to-end ASR Systems

Marc Delcroix, Shinji Watanabe, Atsunori Ogawa, Shigeki Karita, and Tomohiro Nakatani

Proceedings of Interspeech 2018
ASR ACL

A Purely End-to-End System for Multi-speaker Speech Recognition

Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, and John R Hershey

In Proceedings of the Annual Meeting of the Association for Computational Linguistics 2018
ASR ICASSP

Speaker adaptation for multichannel end-to-end speech recognition

Tsubasa Ochiai, Shinji Watanabe, Shigeru Katagiri, Takaaki Hori, and John Hershey

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018
ASR ICASSP

An end-to-end language-tracking speech recognizer for mixed-language speech

Hiroshi Seki, Shinji Watanabe, Takaaki Hori, Jonathan Le Roux, and John R Hershey

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018
ASR ICASSP

End-to-end multi-speaker speech recognition

Shane Settle, Jonathan Le Roux, Takaaki Hori, Shinji Watanabe, and John R Hershey

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018