Related papers: Speaker Cluster-Based Speaker Adaptive Training fo…
In speaker diarisation, speaker embedding extraction models often suffer from the mismatch between their training loss functions and the speaker clustering method. In this paper, we propose the method of spectral clustering-aware learning…
Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…
Automatic classification of disordered speech can provide an objective tool for identifying the presence and severity of speech impairment. Classification approaches can also help identify hard-to-recognize speech samples to teach ASR…
Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant…
Selective auditory attention decoding aims to identify the speaker of interest from listeners' neural signals, such as electroencephalography (EEG), in the presence of multiple concurrent speakers. Most existing methods operate at the…
Data efficient voice cloning aims at synthesizing target speaker's voice with only a few enrollment samples at hand. To this end, speaker adaptation and speaker encoding are two typical methods based on base model trained from multiple…
This paper proposes a novel Sequence-to-Sequence (Seq2Seq) model integrating the structure of Hidden Semi-Markov Models (HSMMs) into its attention mechanism. In speech synthesis, it has been shown that methods based on Seq2Seq models using…
Recent single-channel speech enhancement methods based on deep neural networks (DNNs) have achieved remarkable results, but there are still generalization problems in real scenes. Like other data-driven methods, DNN-based speech enhancement…
Although deep learning (DL) has achieved notable progress in speech enhancement (SE), further research is still required for a DL-based SE system to adapt effectively and efficiently to particular speakers. In this study, we propose a novel…
Discovering speaker independent acoustic units purely from spoken input is known to be a hard problem. In this work we propose an unsupervised speaker normalization technique prior to unit discovery. It is based on separating speaker…
This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…
With recent advancements in voice cloning, the performance of speech synthesis for a target speaker has been rendered similar to the human level. However, autoregressive voice cloning systems still suffer from text alignment failures,…
Speaker identification typically involves three stages. First, a front-end speaker embedding model is trained to embed utterance and speaker profiles. Second, a scoring function is applied between a runtime utterance and each speaker…
This paper presents a system for the 2024 Text-Dependent Speaker Verification (TdSV) Challenge. The system achieved a Minimum Detection Cost Function (MinDCF) of 0.0461 and an Equal Error Rate (EER) of 1.3\%. Our approach focused on…
We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of low-dimensional subspaces. To that end, the training posteriors are used for dictionary learning and sparse coding.…
Automatic speaker diarization techniques typically involve a two-stage processing approach where audio segments of fixed duration are converted to vector representations in the first stage. This is followed by an unsupervised clustering of…
Human can recognize speech, as well as the peculiar accent of the speech simultaneously. However, present state-of-the-art ASR system can rarely do that. In this paper, we propose a multilingual approach to recognizing English speech, and…
Improving distant speech recognition is a crucial step towards flexible human-machine interfaces. Current technology, however, still exhibits a lack of robustness, especially when adverse acoustic conditions are met. Despite the significant…
Articulatory-to-acoustic (forward) mapping is a technique to predict speech using various articulatory acquisition techniques (e.g. ultrasound tongue imaging, lip video). Real-time MRI (rtMRI) of the vocal tract has not been used before for…
We propose SpeakerNet - a new neural architecture for speaker recognition and speaker verification tasks. It is composed of residual blocks with 1D depth-wise separable convolutions, batch-normalization, and ReLU layers. This architecture…