216 citations · 521 across the 32 of their papers we have counts for
9 papers · 1 filter
DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputs
Desh Raj, Leibny Paola Garcia-Perera, Zili Huang +4
Several advances have been made recently towards handling overlapping speech for speaker diarization. Since speech and natural language tasks often benefit from ensemble techniques…
Frustratingly Easy Noise-aware Training of Acoustic Models
Desh Raj, Jesus Villalba, Daniel Povey +1
Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based…
Neural Language Modeling With Implicit Cache Pointers
Ke Li, Daniel Povey, Sanjeev Khudanpur
A cache-inspired approach is proposed for neural language models (LMs) to improve long-range dependency and better predict rare words from long contexts. This approach is a simpler…
Mixture of Speaker-type PLDAs for Children's Speech Diarization
Jiamin Xie, Suzanna Sia, Paola Garcia +2
In diarization, the PLDA is typically used to model an inference structure which assumes the variation in speech segments be induced by various speakers. The speaker variation is t…
Efficient MDI Adaptation for n-gram Language Models
Ruizhe Huang, Ke Li, Ashish Arora +2
This paper presents an efficient algorithm for n-gram language model adaptation under the minimum discrimination information (MDI) principle, where an out-of-domain language model…
PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR
Yiwen Shao, Yiming Wang, Daniel Povey +1
We present PyChain, a fully parallelized PyTorch implementation of end-to-end lattice-free maximum mutual information (LF-MMI) training for the so-called \emph{chain models} in the…
Multistream CNN for Robust Acoustic Modeling
Kyu J. Han, Jing Pan, Venkata Krishna Naveen Tadala +2
This paper proposes multistream CNN, a novel neural network architecture for robust acoustic modeling in speech recognition tasks. The proposed architecture processes input speech…
Wake Word Detection with Alignment-Free Lattice-Free MMI
Yiming Wang, Hang Lv, Daniel Povey +2
Always-on spoken language interfaces, e.g. personal digital assistants, rely on a wake word to start processing spoken input. We present novel methods to train a hybrid DNN/HMM wak…
Speaker Diarization with Region Proposal Network
Zili Huang, Shinji Watanabe, Yusuke Fujita +4
Speaker diarization is an important pre-processing step for many speech applications, and it aims to solve the "who spoke when" problem. Although the standard diarization systems c…