Related papers: Distortion-controlled Training for End-to-end Reve…
The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity. In this paper, we present Personalized…
In the recent years, singing voice separation systems showed increased performance due to the use of supervised training. The design of training datasets is known as a crucial factor in the performance of such systems. We investigate on how…
Although recent advances in deep learning technology improved automatic speech recognition (ASR), it remains difficult to recognize speech when it overlaps other people's voices. Speech separation or extraction is often used as a front-end…
End-to-end (E2E) neural modeling has emerged as one predominant school of thought to develop computer-assisted language training (CAPT) systems, showing competitive performance to conventional pronunciation-scoring based methods. However,…
The current dominant approach for neural speech enhancement is based on supervised learning by using simulated training data. The trained models, however, often exhibit limited generalizability to real-recorded data. To address this, this…
Auditory attention decoding (AAD) is the process of identifying the attended speech in a multi-talker environment using brain signals, typically recorded through electroencephalography (EEG). Over the past decade, AAD has undergone…
Acoustic echo cancellation (AEC) remains challenging in real-world environments due to nonlinear distortions caused by low-cost loudspeakers and complex room acoustics. To mitigate these issues, we introduce a dual-microphone configuration,…
We propose mixture to mixture (M2M) training, a weakly-supervised neural speech separation algorithm that leverages close-talk mixtures as a weak supervision for training discriminative models to separate far-field mixtures. Our idea is…
This paper addresses the prevalent issue of incorrect speech output in audio-visual speech enhancement (AVSE) systems, which is often caused by poor video quality and mismatched training and test data. We introduce a post-processing…
Consider a multichannel Ambisonic recording containing a mixture of several reverberant speech signals. Retreiving the reverberant Ambisonic signals corresponding to the individual speech sources blindly from the mixture is a challenging…
Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task. By contrast, this paper aims to investigate the task of end-to-end speech recognition and disfluency removal.…
We study the single-channel source separation problem involving orthogonal frequency-division multiplexing (OFDM) signals, which are ubiquitous in many modern-day digital communication systems. Related efforts have been pursued in monaural…
When beginners learn to speak a non-native language, it is difficult for them to judge for themselves whether they are speaking well. Therefore, computer-assisted pronunciation training systems are used to detect learner mispronunciations.…
This paper addresses the combination of complementary parallel speech recognition systems to reduce the error rate of speech recognition systems operating in real highly-reverberant environments. First, the testing environment consists of…
Proper nouns present a challenge for end-to-end (E2E) automatic speech recognition (ASR) systems in that a particular name may appear only rarely during training, and may have a pronunciation similar to that of a more common word. Unlike…
Acoustic Echo Cancellation (AEC) plays a key role in speech interaction by suppressing the echo received at microphone introduced by acoustic reverberations from loudspeakers. Since the performance of linear adaptive filter (AF) would…
Despite the recent significant advances witnessed in end-to-end (E2E) ASR system for code-switching, hunger for audio-text paired data limits the further improvement of the models' performance. In this paper, we propose a decoupled…
Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and…
Acoustic echo cancellation (AEC) is an important speech signal processing technology that can remove echoes from microphone signals to enable natural-sounding full-duplex speech communication. While single-channel AEC is widely adopted,…
Self-supervised-learning-based pre-trained models for speech data, such as Wav2Vec 2.0 (W2V2), have become the backbone of many speech tasks. In this paper, to achieve speaker diarisation and speech recognition using a single model, a…