no code implementations • 22 Mar 2023 • Samik Sadhu, Hynek Hermansky
We show that training a multi-headed self-attention-based deep network to predict deleted, information-dense 2-8 Hz speech modulations over a 1. 5-second section of a speech utterance is an effective way to make machines learn to extract speech modulations using time-domain contextual information.
no code implementations • 7 Mar 2023 • Martin Sustek, Samik Sadhu, Lukas Burget, Hynek Hermansky, Jesus Villalba, Laureano Moro-Velazquez, Najim Dehak
The JEM training relies on "positive examples" (i. e. examples from the training data set) as well as on "negative examples", which are samples from the modeled distribution $p(x)$ generated by means of Stochastic Gradient Langevin Dynamics (SGLD).
no code implementations • 30 Sep 2022 • Samik Sadhu, Hynek Hermansky
We present a method to remove unknown convolutive noise introduced to speech by reverberations of recording environments, utilizing some amount of training speech data from the reverberant environment, and any available non-reverberant speech data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 31 Mar 2022 • Samik Sadhu, Hynek Hermansky
How important are different temporal speech modulations for speech recognition?
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
2 code implementations • 25 Mar 2021 • Samik Sadhu, Hynek Hermansky
We propose a technique to compute spectrograms using Frequency Domain Linear Prediction (FDLP) that uses all-pole models to fit the squared Hilbert envelope of speech in different frequency sub-bands.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 5 Feb 2021 • Ruizhi Li, Gregory Sell, Hynek Hermansky
Performance degradation of an Automatic Speech Recognition (ASR) system is commonly observed when the test acoustic condition is different from training.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 23 Oct 2019 • Ruizhi Li, Gregory Sell, Xiaofei Wang, Shinji Watanabe, Hynek Hermansky
The multi-stream paradigm of audio processing, in which several sources are simultaneously considered, has been an active research area for information fusion.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 17 Jun 2019 • Ruizhi Li, Xiaofei Wang, Sri Harish Mallidi, Shinji Watanabe, Takaaki Hori, Hynek Hermansky
Two representative framework have been proposed and discussed, which are Multi-Encoder Multi-Resolution (MEM-Res) framework and Multi-Encoder Multi-Array (MEM-Array) framework, respectively.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 9 Apr 2019 • Ruizhi Li, Gregory Sell, Hynek Hermansky
Measuring performance of an automatic speech recognition (ASR) system without ground-truth could be beneficial in many scenarios, especially with data from unseen domains, where performance can be highly inconsistent.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 8 Apr 2019 • Xiaofei Wang, Jinyi Yang, Ruizhi Li, Samik Sadhu, Hynek Hermansky
Quality of data plays an important role in most deep learning tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 12 Nov 2018 • Ruizhi Li, Xiaofei Wang, Sri Harish Mallidi, Takaaki Hori, Shinji Watanabe, Hynek Hermansky
In this work, we present a novel Multi-Encoder Multi-Resolution (MEMR) framework based on the joint CTC/Attention model.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 12 Nov 2018 • Xiaofei Wang, Ruizhi Li, Sri Harish Mallid, Takaaki Hori, Shinji Watanabe, Hynek Hermansky
Automatic Speech Recognition (ASR) using multiple microphone arrays has achieved great success in the far-field robustness.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • NeurIPS 2008 • Daphna Weinshall, Hynek Hermansky, Alon Zweig, Jie Luo, Holly Jimison, Frank Ohl, Misha Pavel
We define a formal framework for the representation and processing of incongruent events: starting from the notion of label hierarchy, we show how partial order on labels can be deduced from such hierarchies.