15 citations · 25 across the 14 of their papers we have counts for
15 papers
Bayesian Learning for Domain-Invariant Speaker Verification and Anti-Spoofing
Jin Li, Man-Wai Mak, Johan Rohdin +2
The performance of automatic speaker verification (ASV) and anti-spoofing drops seriously under real-world domain mismatch conditions. The relaxed instance frequency-wise normaliza…
Self-supervised Learning with Speech Modulation Dropout
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 utteran…
Stabilized training of joint energy-based models and their practical applications
Martin Sustek, Samik Sadhu, Lukas Burget +4
The recently proposed Joint Energy-based Model (JEM) interprets discriminatively trained classifier as an energy model, which is also trained as a generative model describ…
Blind Signal Dereverberation for Machine Speech Recognition
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 rev…
Importance of Different Temporal Modulations of Speech: A Tale of Two Perspectives
Samik Sadhu, Hynek Hermansky
How important are different temporal speech modulations for speech recognition? We answer this question from two complementary perspectives. Firstly, we quantify the amount of phon…
Complex Frequency Domain Linear Prediction: A Tool to Compute Modulation Spectrum of Speech
Samik Sadhu, Hynek Hermansky
Conventional Frequency Domain Linear Prediction (FDLP) technique models the squared Hilbert envelope of speech with varied degrees of approximation which can be sampled at the requ…
Radically Old Way of Computing Spectra: Applications in End-to-End ASR
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…
Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream End-to-End ASR
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. Hence, it is essential to…
A practical two-stage training strategy for multi-stream end-to-end speech recognition
Ruizhi Li, Gregory Sell, Xiaofei Wang +2
The multi-stream paradigm of audio processing, in which several sources are simultaneously considered, has been an active research area for information fusion. Our previous study o…
Multi-Stream End-to-End Speech Recognition
Ruizhi Li, Xiaofei Wang, Sri Harish Mallidi +3
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The…
Performance Monitoring for End-to-End Speech Recognition
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 pe…
Exploring Methods for the Automatic Detection of Errors in Manual Transcription
Xiaofei Wang, Jinyi Yang, Ruizhi Li +2
Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually…
Multi-encoder multi-resolution framework for end-to-end speech recognition
Ruizhi Li, Xiaofei Wang, Sri Harish Mallidi +3
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint…
Stream attention-based multi-array end-to-end speech recognition
Xiaofei Wang, Ruizhi Li, Sri Harish Mallid +3
Automatic Speech Recognition (ASR) using multiple microphone arrays has achieved great success in the far-field robustness. Taking advantage of all the information that each array…
Stream Attention for far-field multi-microphone ASR
Xiaofei Wang, Yonghong Yan, Hynek Hermansky
A stream attention framework has been applied to the posterior probabilities of the deep neural network (DNN) to improve the far-field automatic speech recognition (ASR) performanc…