Related papers: System Combination for Short Utterance Speaker Rec…

Model size and complexity remain the biggest challenges in the deployment of speech enhancement and separation systems on low-resource devices such as earphones and hearing aids. Although methods such as compression, distillation and…

Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…

Driven by large scale datasets and LLM based architectures, automatic speech recognition (ASR) systems have achieved remarkable improvements in accuracy. However, challenges persist for domain-specific terminology, and short utterances…

In this work, we propose a classifier for distinguishing device-directed queries from background speech in the context of interactions with voice assistants. Applications include rejection of false wake-ups or unintended interactions as…

This paper reports our work on building up a Cantonese Speech-to-Text (STT) system with a syllable based acoustic model. This is a part of an effort in building a STT system to aid dyslexic students who have cognitive deficiency in writing…

This paper introduces the performance evaluation of statistical approaches for TextIndependent speaker recognition system using source feature. Linear prediction LP residual is used as a representation of excitation information in speech.…

This paper introduces a set of acoustic modeling techniques for utterance verification (UV) based continuous speech recognition (CSR). Utterance verification in this work implies the ability to determine when portions of a hypothesized word…

A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are…

We present state-of-the-art automatic speech recognition (ASR) systems employing a standard hybrid DNN/HMM architecture compared to an attention-based encoder-decoder design for the LibriSpeech task. Detailed descriptions of the system…

Acoustic models based on long short-term memory recurrent neural networks (LSTM-RNNs) were applied to statistical parametric speech synthesis (SPSS) and showed significant improvements in naturalness and latency over those based on hidden…

Deep neural networks have shown promising potential for ultrasound-to-speech conversion task towards Silent Speech Interfaces. In this work, we applied two Conformer-based DNN architectures (Base and one with bi-LSTM) for this task.…

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on…

Many neural network speaker recognition systems model each speaker using a fixed-dimensional embedding vector. These embeddings are generally compared using either linear or 2nd-order scoring and, until recently, do not handle…

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in…

Speaker embeddings are promising identity-related features that can enhance the identity assignment performance of a tracking system by leveraging its spatial predictions, i.e, by performing identity reassignment. Common speaker embedding…

This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to…

Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing…

Universal speech enhancement aims at handling inputs with various speech distortions and recording conditions. In this work, we propose a novel hybrid architecture that synergizes the signal fidelity of discriminative modeling with the…

Recently, more and more zero-shot voice conversion algorithms have been proposed. As a fundamental part of zero-shot voice conversion, speaker embeddings are the key to improving the converted speech's speaker similarity. In this paper, we…

Deep learning models are widely used for speaker recognition and spoofing speech detection. We propose the GMM-ResNet2 for synthesis speech detection. Compared with the previous GMM-ResNet model, GMM-ResNet2 has four improvements. Firstly,…