Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

Recently, the end-to-end approach has proven its efficacy in monaural multi-speaker speech
recognition. However, high word error rates (WERs) still prevent these systems from being …

For real-world speech recognition applications, noise robustness is still a challenge. In this
work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy …

Transformers are powerful neural architectures that allow integrating different modalities
using attention mechanisms. In this paper, we leverage the neural transformer architectures …

The traditional generalized sidelobe canceller (GSC) is a common speech enhancement
front end to improve the noise robustness of automatic speech recognition (ASR) systems in …

With the surge of online meetings, it has become more critical than ever to provide high-
quality speech audio and live captioning under various noise conditions. However, most …

In this work, we propose a GAN-based method to generate synthetic data for speech
emotion recognition. Specifically, we investigate the usage of GANs for capturing the data …

Multi-speaker speech recognition has been one of the keychallenges in conversation
transcription as it breaks the singleactive speaker assumption employed by most state-of-the …

Self-supervised speech pre-training methods have developed rapidly in recent years, which
show to be very effective for many near-field single-channel speech tasks. However, far-field …

When a sufficiently large far-field training data is presented, jointly optimizing a multichannel
frontend and an end-to-end (E2E) Automatic Speech Recognition (ASR) backend shows …