17 accepted papers
The Mixture of Experts (MoE) model is a promising approach for handling code-switching speech recognition (CS-ASR) tasks. However, the existing CS-ASR work on MoE has yet to leverage the advantages of MoE’s parameter scaling ability fully. This work proposes DLG-MoE, a Dynamic Language Group-based M…
Recently, flow matching based speech synthesis has significantly enhanced the quality of synthesized speech while reducing the number of inference steps. In this paper, we introduce SlimSpeech, a lightweight and efficient speech synthesis system based on rectified flow. We have built upon the existi…
End-to-end (E2E) multi-speaker speech recognition with the serialized output training (SOT) strategy demonstrates good performance in modeling diverse speaker scenarios. However, the E2E architecture doesn’t explicitly address the modeling of overlapping speech areas, potentially limiting the model’…
The style transfer task in Text-to-Speech (TTS) refers to the process of transferring style information into text content to generate corresponding speech with a specific style. However, most existing style transfer approaches are either based on fixed emotional labels or reference speech clips, whi…
The diffusion models including Denoising Diffusion Probabilistic Models (DDPM) and score-based generative models have demonstrated excellent performance in speech synthesis tasks. However, its effectiveness comes at the cost of numerous sampling steps, resulting in prolonged sampling time required t…
Recently, pre-trained models (PTMs) have been extensively applied in speaker verification (SV) and greatly boosted system performance. However, mainstream PTMs currently concentrate on using frame-level universal representations. In this paper, we propose a novel pre-training framework that jointly…
The clustering algorithm plays a crucial role in speaker diarization systems. However, traditional clustering algorithms suffer from the complex distribution of speaker embeddings and lack of digging potential relationships between speakers in a session. We propose a novel graph-based clustering app…
Model Agnostic Meta-Learning (MAML) is an effective meta-learning algorithm for low-resource automatic speech recognition (ASR). It uses gradient descent to learn the initialization parameters of the model through various languages, making the model quickly adapt to unseen low-resource languages. Bu…
In this paper, we present our work in track 2 of the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. We built a cascaded system and explored different acoustic front-ends and end-to-end speech recognition back-ends based on multimodal. To promote effective fusion between the d…
Transformer has achieved extraordinary performance in Natural Language Processing and Computer Vision tasks thanks to its powerful self-attention mechanism, and its variant Conformer has become a state-of-the-art architecture in the field of Automatic Speech Recognition (ASR). However, the main-stre…
Recently, the fine-tuning pre-trained model framework has emerged as a promising paradigm for speech-processing tasks. In this study, we present a novel strategy for unsupervised speaker verification using the Sub-structure of Pre-Trained Model (Sub-PTM), which consists of a CNN-based feature extrac…
Unsupervised clustering on speakers is becoming increasingly important for its potential uses in semi-supervised learning. In reality, we are often presented with enormous amounts of unlabeled data from multi-party meetings and discussions. An effective unsupervised clustering approach would allow u…
In this paper, we introduce a new open source toolkit for automatic speaker verification (ASV), named ASV-Subtools. Adopting PyTorch as main deep learning engine and Kaldi toolkit for data processing, ASV-Subtools allows users to develop modern speaker recognizers flexibly and efficiently. The toolk…
End-to-end speech recognition has achieved good recognition performance on standard English pronunciation datasets. However, one prominent problem with end-to-end speech recognition systems is that non-native English speakers tend to have complex and varied accents, which reduces the accuracy of Eng…
With the development of deep learning, end-to-end neural text-to-speech (TTS) systems have achieved significant improvements in high-quality speech synthesis. However, most of these systems are attention-based autoregressive models, resulting in slow synthesis speed and large model parameters. In ad…
Under noisy environments, to achieve the robust performance of speaker recognition is still a challenging task. Motivated by the promising performance of multi-task training in a variety of image processing tasks, we explore the potential of multitask adversarial training for learning a noise-robust…
Currently, the state-of-the-art speaker verification system is based on i-vector and PLDA. However, PLDA requires tens of thousands of development data from many speakers. This makes it difficult to learn the PLDA parameters for a domain with scarce data. In this paper, we propose an effective trans…